© 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. 45252
    Prev
    Next
    INDEX
    Explanations

    Figure, gallery, time, fit

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

    EndeavourOS

    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
    midt
    0.49
    اً
    0.47
     دوم
    0.45
    ভাবে
    0.45
     faut
    0.44
    resser
    0.44
     اختبار
    0.44
     الن
    0.44
     NDA
    0.44
    akers
    0.43
    POSITIVE LOGITS
    \<
    0.57
    UZ
    0.54
    Kb
    0.52
    遨
    0.49
    WK
    0.49
     imagina
    0.47
    Yo
    0.46
    ("<
    0.45
    在上
    0.45
    HK
    0.45
    Activations Density 0.001%

    No Known Activations