© 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. 101924
    Prev
    Next
    INDEX
    Explanations

    {verb} {article}

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

    potential consequences

    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
    废物
    0.51
    សម្រាប់ការ
    0.50
     HTMLSc
    0.50
    marshalO
    0.49
    বিহীন
    0.49
    脇
    0.46
    MessageNow
    0.46
    ósfera
    0.46
    मील
    0.46
    秞
    0.46
    POSITIVE LOGITS
     is
    0.56
     man
    0.53
     maintains
    0.52
     Greek
    0.50
     provides
    0.49
     perseverance
    0.48
     concentrates
    0.47
     carries
    0.46
     braces
    0.46
     indexes
    0.46
    Activations Density 0.001%

    No Known Activations