© 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. 17037
    Prev
    Next
    INDEX
    Explanations

    amongst today

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

    optimizer states (momentum, variance)

    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
    朢
    0.51
    หมือน
    0.50
    覺
    0.50
    блиоте
    0.49
    ძლიათ
    0.49
    но
    0.47
     інші
    0.47
    다른
    0.47
    堹
    0.46
    дру
    0.46
    POSITIVE LOGITS
    0.59
     Voluntary
    0.53
     Travel
    0.52
     from
    0.52
     Journal
    0.51
     Knoll
    0.50
     Daily
    0.49
     Goat
    0.49
     Successful
    0.49
     for
    0.49
    Activations Density 0.000%

    No Known Activations