© 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. 76250
    Prev
    Next
    INDEX
    Explanations

    return, come back

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

    actions and concepts

    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
     bhas
    0.50
     kitabı
    0.47
    རྒྱ
    0.46
    یکٹر
    0.46
    ണ്ടും
    0.45
     کتاب
    0.45
    ।
    0.45
     externalities
    0.45
     manuals
    0.44
     обстоя
    0.44
    POSITIVE LOGITS
    ují
    0.55
    ujeme
    0.48
    راجعه
    0.46
    ukat
    0.46
    á
    0.46
    ysta
    0.44
     mohou
    0.43
    उनके
    0.43
    ứt
    0.43
    oste
    0.43
    Activations Density 0.001%

    No Known Activations