© 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. 26138
    Prev
    Next
    INDEX
    Explanations

    it's not being

    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
    <unused62>
    0.47
    <unused61>
    0.46
    R
    0.43
    RELATED
    0.42
     Initializes
    0.42
    몬
    0.41
     will
    0.39
    D
    0.39
     comparable
    0.38
    Will
    0.38
    POSITIVE LOGITS
     سلمان
    0.50
    calup
    0.48
     атмосфер
    0.46
     сущ
    0.45
     bereits
    0.44
     atmosfer
    0.44
     невозможно
    0.43
     ശേഷം
    0.43
     femora
    0.43
     superstit
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.