© 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. 168378
    Prev
    Next
    INDEX
    Explanations

    Rectangle stickers

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

    configuration and setup

    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
    㛣
    0.50
     elenco
    0.50
    čili
    0.48
    螌
    0.48
    礽
    0.47
    ани
    0.47
    睄
    0.47
    ArrowToggle
    0.46
     integro
    0.46
    aktur
    0.46
    POSITIVE LOGITS
    ே
    0.49
    k
    0.47
     Cancer
    0.46
    c
    0.46
    Castle
    0.45
    <b>
    0.44
    BA
    0.44
    IN
    0.43
     +
    0.43
     A
    0.43
    Activations Density 0.000%

    No Known Activations