© 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. 206723
    Prev
    Next
    INDEX
    Explanations

    Attracting, producing, requiring

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

    unique elements preserving order

    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
    '
    0.57
    ’
    0.57
    ท
    0.56
    なので
    0.54
    /
    0.52
    ،
    0.48
    對於
    0.47
    ，
    0.47
    だから
    0.46
    गा
    0.46
    POSITIVE LOGITS
    ರಿಗೆ
    0.46
     shik
    0.46
     પ્રથમ
    0.46
    hamento
    0.46
    első
    0.46
    ர்வ
    0.45
     oftent
    0.44
    <unused28>
    0.44
     }]);
    0.44
    মন্ত
    0.44
    Activations Density 0.001%

    No Known Activations