© 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. 47496
    Prev
    Next
    INDEX
    Explanations

    unverified claims

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

    uncertainty and speculation

    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
     ఎం
    0.48
     મોબાઇલ
    0.46
    पिछले
    0.46
    衡量
    0.45
    लेबल
    0.45
     స్థాయిలో
    0.45
     Bereichen
    0.44
    ㅐ
    0.44
    맵
    0.43
    كيف
    0.43
    POSITIVE LOGITS
     alleged
    0.95
    据说
    0.95
     rumored
    0.91
    传说
    0.87
     údaj
    0.84
     putative
    0.83
     purported
    0.82
     conjectured
    0.82
     presumed
    0.81
     allegedly
    0.79
    Activations Density 0.058%

    No Known Activations