© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 16265
    Prev
    Next
    INDEX
    Explanations

    too something (degree/excess)

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on occurrences of the adverb “too.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the phrase "too" followed by an adjective or adverb, typically in expressions emphasizing excess or degree.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases signaling excess or overabundance, where an intensifier marks something as overly great in degree or quantity.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ่
    1.38
     eradicate
    1.27
     améli
    1.25
    voorbeeld
    1.25
     dotycz
    1.22
    लिये
    1.21
     accommodate
    1.20
     erreur
    1.19
    ামুটি
    1.18
     rzecz
    1.17
    POSITIVE LOGITS
    너무
    1.64
    o
    1.36
    过于
    1.27
    ing
    1.25
    og
    1.20
    多的
    1.18
    om
    1.15
    ة
    1.08
    Π
    1.04
    Too
    1.03
    Activations Density 0.027%

    No Known Activations