© 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. 175971
    Prev
    Next
    INDEX
    Explanations

    numbers, specific words, and punctuation

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

    scoring explanations

    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
     цього
    0.51
     ஆகவே
    0.50
    ectable
    0.49
    users
    0.48
    songs
    0.48
    Ŵ
    0.48
    Users
    0.47
    USERS
    0.46
    ₤
    0.46
    ivores
    0.45
    POSITIVE LOGITS
     janeiro
    0.47
    在地
    0.46
    ौनक
    0.45
     earliest
    0.44
     Veer
    0.43
     hae
    0.42
    陂
    0.42
     Ksh
    0.41
    硫酸
    0.40
     Wayback
    0.40
    Activations Density 0.000%

    No Known Activations