© 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. 175267
    Prev
    Next
    INDEX
    Explanations

    people, tornado, parent, college, walls, close, Zoo

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

    building a house

    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
     жиз
    0.53
    adios
    0.50
    危
    0.49
    they
    0.49
    them
    0.48
    пада
    0.46
     montaña
    0.45
    ту
    0.44
     우
    0.44
    우
    0.44
    POSITIVE LOGITS
    راہیم
    0.48
     Greer
    0.48
     Masaki
    0.45
     reconstituted
    0.45
     Tiro
    0.45
     Aung
    0.44
     interwoven
    0.44
     ಅನೇಕ
    0.43
     numerose
    0.43
    ('');
    0.43
    Activations Density 0.000%

    No Known Activations