© 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. 44610
    Prev
    Next
    INDEX
    Explanations

    technical/legal terms followed by descriptions

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

    hardware repair and explanations

    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
    i
    0.59
    rd
    0.57
    src
    0.54
    re
    0.50
    www
    0.50
    ms
    0.49
    ko
    0.49
    ro
    0.49
    temperature
    0.48
    benius
    0.48
    POSITIVE LOGITS
    лювання
    0.50
     nhi
    0.49
    лькі
    0.49
     американский
    0.49
    췄
    0.48
     insuffis
    0.47
     océano
    0.47
     childnya
    0.46
    GISL
    0.46
     achats
    0.46
    Activations Density 0.000%

    No Known Activations