© 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. 180629
    Prev
    Next
    INDEX
    Explanations

    on behalf, identify, coasts, off

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

    attempting to do something

    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
    LEC
    0.49
    ADY
    0.49
     過
    0.48
    PLAN
    0.47
     ଯ
    0.47
    NEY
    0.46
    LEMENT
    0.46
    LE
    0.46
     halen
    0.45
     跳转
    0.45
    POSITIVE LOGITS
    濑
    0.48
    ف
    0.46
     جیل
    0.46
     melawan
    0.45
    ກ
    0.45
    وک
    0.45
    یکی
    0.41
    چه
    0.41
     دیگری
    0.41
    راث
    0.41
    Activations Density 0.001%

    No Known Activations