© 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. 44404
    Prev
    Next
    INDEX
    Explanations

    permission slip or research

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

    verify power or state changes

    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
    ization
    0.54
     หลาย
    0.50
     首先
    0.49
    2
    0.49
    Relation
    0.49
    ize
    0.46
    麦
    0.45
    Assuming
    0.44
    5
    0.44
     해주
    0.44
    POSITIVE LOGITS
    ૂર્વ
    0.52
     finanz
    0.50
     keeping
    0.49
     preserving
    0.49
    ково
    0.49
     keep
    0.48
     confining
    0.47
     giữ
    0.47
    ુભ
    0.47
     curbing
    0.47
    Activations Density 0.000%

    No Known Activations