© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 38257
    Prev
    Next
    INDEX
    Explanations

    journals, envelopes, registers

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

    dynamic interactions or states

    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
     Vegetation
    0.44
     Published
    0.43
    و
    0.43
    Nigeria
    0.42
    軟件
    0.42
    ٹری
    0.41
     Він
    0.40
     нати
    0.40
     Great
    0.39
     \
    0.39
    POSITIVE LOGITS
    '&
    0.54
    LF
    0.47
     aldehyde
    0.46
    olphe
    0.43
    adas
    0.43
    &
    0.42
    <unused1901>
    0.42
    SHORT
    0.42
    
    0.42
    ריך
    0.41
    Activations Density 0.000%

    No Known Activations