© 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. 95579
    Prev
    Next
    INDEX
    Explanations

    trash collection, collective bargaining, neglect

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

    creating data or performing critical checks

    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
    et
    0.48
    EVENTS
    0.47
    one
    0.46
    DEVELOP
    0.46
    t
    0.44
    чений
    0.43
    <0x8C>
    0.43
    TRANSFER
    0.43
    YE
    0.43
    একদিন
    0.43
    POSITIVE LOGITS
     பட்டிய
    0.48
     unt
    0.47
     போட்டிய
    0.47
    ियों
    0.47
     thermost
    0.47
     게시
    0.47
     brooding
    0.46
     untreated
    0.46
    ス
    0.46
     shun
    0.46
    Activations Density 0.000%

    No Known Activations