© 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. 112893
    Prev
    Next
    INDEX
    Explanations

    behind the scene

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

    explaining meanings or consequences

    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
     పనిచే
    0.53
     собственно
    0.47
     செயல
    0.46
    eringen
    0.45
    实行
    0.45
     zaji
    0.45
    茴
    0.44
     இரண்ட
    0.44
    uanya
    0.44
    форми
    0.44
    POSITIVE LOGITS
    v
    0.54
     v
    0.52
     intensities
    0.52
     payouts
    0.49
     matchups
    0.48
     il
    0.46
     probabilities
    0.45
    が
    0.44
     interactions
    0.44
     premiums
    0.44
    Activations Density 0.000%

    No Known Activations