© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 145002
    Prev
    Next
    INDEX
    Explanations

    specific game instructions

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

    records timing information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    dą
    0.54
    aménagement
    0.51
     meat
    0.50
    urably
    0.48
    meat
    0.47
    ⼈
    0.47
    わせ
    0.46
    バリ
    0.46
     sorties
    0.46
    datasets
    0.45
    POSITIVE LOGITS
     Abt
    0.46
    往下
    0.43
    க்குள்
    0.43
     sorpre
    0.43
     Appart
    0.43
     Geophys
    0.42
    %{
    0.42
     Einst
    0.42
    t
    0.42
     Zentrum
    0.42
    Activations Density 0.001%

    No Known Activations