© 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. 189157
    Prev
    Next
    INDEX
    Explanations

    foreign, emoji, or symbol content

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

    direct focus and titles

    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
    켈
    0.48
    urant
    0.48
    urous
    0.46
     परिस्थितीत
    0.46
     monde
    0.46
     விஞ்ஞான
    0.45
    学院
    0.45
     Восто
    0.44
     MMS
    0.44
     получать
    0.44
    POSITIVE LOGITS
    σει
    0.49
     χρη
    0.47
     απα
    0.47
    🦓
    0.45
     grenades
    0.44
     دليل
    0.44
    ResBuffer
    0.44
    Scoped
    0.44
    是因为
    0.44
    ים
    0.43
    Activations Density 0.001%

    No Known Activations