© 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. 15882
    Prev
    Next
    INDEX
    Explanations

    most [noun]

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

    The neuron fires on majority‐indicating quantifiers (e.g. “Most,” “majority of,” “will”) that generalize over a population.

    oai_token-act-pair · o4-miniTriggered 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
    SANITIZE
    1.16
    AK
    1.11
    ﺒ
    1.11
    thisTrack
    1.10
     različ
    1.09
    빽
    1.09
     Еще
    1.09
    OR
    1.06
     Certaines
    1.05
    ῴ
    1.05
    POSITIVE LOGITS
    ع
    1.30
     importantly
    1.27
    ことを
    1.19
     قریب
    1.19
     (>
    1.15
    с
    1.13
    s
    1.13
    此之外
    1.09
    ς
    1.07
    it
    1.05
    Activations Density 0.165%

    No Known Activations