© 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. 89806
    Prev
    Next
    INDEX
    Explanations

    human physical attributes

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

    weight lifted

    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
    0.49
    in
    0.46
     provoked
    0.46
     aware
    0.45
    а
    0.45
     encouraged
    0.44
     <
    0.44
    и
    0.44
     irrit
    0.43
    ›
    0.43
    POSITIVE LOGITS
    匪
    0.51
     skute
    0.50
     maig
    0.50
     boulevard
    0.46
     condado
    0.46
    мя
    0.46
     turnaround
    0.45
     සා
    0.43
     crc
    0.43
     résultat
    0.43
    Activations Density 0.000%

    No Known Activations