© 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. 15771
    Prev
    Next
    INDEX
    Explanations

    Person 1 and Person 2

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

    This neuron responds to salient content words—i.e. the key nouns, verbs, and adjectives that carry the main meaning of the text.

    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
     "*************
    0.92
     thắng
    0.90
     browserSync
    0.88
     выда
    0.87
     elevado
    0.86
     pós
    0.86
     עבור
    0.86
     lãi
    0.86
     εξ
    0.85
     entscheiden
    0.85
    POSITIVE LOGITS
    Y
    1.17
    et
    1.10
    er
    0.96
    I
    0.95
    H
    0.93
    as
    0.89
    u
    0.88
    E
    0.85
    in
    0.84
    M
    0.82
    Activations Density 0.000%

    No Known Activations