© 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. 206657
    Prev
    Next
    INDEX
    Explanations

    event ready

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

    specific file types or common formats

    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
    revoke
    0.47
    դ
    0.47
    рова
    0.47
    ხვევ
    0.46
    น
    0.45
    на
    0.45
    wenn
    0.45
    ровать
    0.44
    decompose
    0.44
    ર
    0.44
    POSITIVE LOGITS
     vins
    0.52
     marche
    0.46
     confid
    0.45
     col
    0.45
     fric
    0.44
     protégé
    0.44
     Zacks
    0.44
     rez
    0.44
     acciones
    0.44
     risen
    0.43
    Activations Density 0.001%

    No Known Activations