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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2234
    Prev
    Next
    INDEX
    Explanations

    numbers followed by pixels or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    MOUNTAINS
    1.91
     Coroner
    1.88
    報道
    1.88
    ランキング
    1.86
     playa
    1.81
    otransferase
    1.80
     Prosecutor
    1.79
    廡
    1.79
    ormány
    1.78
    izlik
    1.77
    POSITIVE LOGITS
     whereas
    0.88
     while
    0.85
     utils
    0.82
    !,
    0.76
     when
    0.75
     here
    0.74
     unless
    0.71
     because
    0.70
     total
    0.68
    ずつ
    0.68
    Activations Density 0.217%

    No Known Activations