© 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. 223608
    Prev
    Next
    INDEX
    Explanations

    locations nationwide and headquarters

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

    client connected from

    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
    PartResult
    0.51
    %),
    0.47
     النسبيه
    0.45
     والاح
    0.43
     शस्त्र
    0.41
    tout
    0.41
    itemList
    0.41
     cataly
    0.41
    #%%
    0.41
    PushMatrix
    0.41
    POSITIVE LOGITS
     ОБ
    0.48
    ρό
    0.45
     ऐप
    0.44
     இணைப்பு
    0.44
    ạt
    0.43
    बीटी
    0.42
    nią
    0.42
     används
    0.41
     சிறந்த
    0.41
    曇
    0.41
    Activations Density 0.000%

    No Known Activations