© 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. 88195
    Prev
    Next
    INDEX
    Explanations

    rationale explanation purpose

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

    Now,

    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
    adors
    0.50
    纵
    0.48
    Viewport
    0.43
    ỏa
    0.43
    c
    0.43
     Programm
    0.42
    cron
    0.42
    các
    0.42
    gll
    0.40
     giản
    0.40
    POSITIVE LOGITS
     tine
    0.48
    kanen
    0.46
     अनिवार
    0.45
     situations
    0.45
     masas
    0.45
     neige
    0.45
    Evidence
    0.44
    ‚‚
    0.44
     uomini
    0.44
    ఉ
    0.44
    Activations Density 0.001%

    No Known Activations