© 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. 88954
    Prev
    Next
    INDEX
    Explanations

    WiFi setting, category, record value, conversation breaks

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

    numbers, symbols, and foreign words

    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
    uma
    0.48
    uyễn
    0.43
     déi
    0.42
     nuestra
    0.42
    两条
    0.40
    ૃ
    0.40
     א
    0.40
    ři
    0.40
    iooni
    0.40
    eniendo
    0.39
    POSITIVE LOGITS
     ወይም
    0.46
     ಸಹ
    0.44
     liquors
    0.42
     nefarious
    0.42
     وين
    0.41
     Prohibition
    0.41
     واللي
    0.40
     Bans
    0.40
     obscurity
    0.39
     ügy
    0.39
    Activations Density 0.000%

    No Known Activations