© 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. 38358
    Prev
    Next
    INDEX
    Explanations

    for learning, that didn, have some

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

    prioritize fairness, experiences, and ability

    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
    a
    0.55
     voie
    0.50
    u
    0.50
     nominee
    0.49
    o
    0.47
     physician
    0.45
     KV
    0.45
     coval
    0.45
     venue
    0.45
     superintendent
    0.45
    POSITIVE LOGITS
    감을
    0.60
    ('['
    0.53
    <unused85>
    0.52
    <unused86>
    0.51
    감
    0.51
    ری
    0.48
    <unused34>
    0.47
    <unused80>
    0.47
    <unused6>
    0.46
    தற்காக
    0.46
    Activations Density 0.000%

    No Known Activations