© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27344
    Prev
    Next
    INDEX
    Explanations

    key pressed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    埚
    0.43
     بنائیں
    0.42
     иш
    0.41
     ecuaciones
    0.41
     idealism
    0.40
     Đáp
    0.40
     గొప్ప
    0.40
     activación
    0.40
    ᶦ
    0.40
    %$$
    0.39
    POSITIVE LOGITS
    0.43
     new
    0.41
     Heartland
    0.40
    http
    0.40
     NEW
    0.39
     source
    0.39
    Kline
    0.39
    android
    0.38
     Arnold
    0.38
     New
    0.38
    Activations Density 0.000%

    No Known Activations