© 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. 196788
    Prev
    Next
    INDEX
    Explanations

    date and time

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

    collocations and grammatical structures

    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
     Hagen
    0.52
    ၜ
    0.50
    稅
    0.50
     Hegel
    0.46
     Mortara
    0.46
    Durch
    0.45
    ジュ
    0.45
     Katzen
    0.45
     Ishikawa
    0.45
     Dubois
    0.45
    POSITIVE LOGITS
    ey
    0.46
     攵
    0.46
     subtle
    0.44
    .]
    0.44
    utf
    0.43
     roof
    0.43
     metro
    0.41
     இசை
    0.41
    ure
    0.41
     liturgical
    0.40
    Activations Density 0.000%

    No Known Activations