© 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. 195690
    Prev
    Next
    INDEX
    Explanations

    play and download

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

    no hasslesno showingsno paymentaudio systemSunday helps

    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
     ниво
    0.53
     Σ
    0.51
     NEVER
    0.49
     esprit
    0.49
     никогда
    0.49
     teamwork
    0.47
     ಈ
    0.47
     zag
    0.47
     senses
    0.46
     Ла
    0.46
    POSITIVE LOGITS
    ari
    0.56
    ist
    0.55
    ة
    0.54
    ann
    0.53
    ية
    0.53
    gifter
    0.52
    alone
    0.50
    os
    0.50
    ruff
    0.49
    pool
    0.48
    Activations Density 0.000%

    No Known Activations