© 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. 186155
    Prev
    Next
    INDEX
    Explanations

    obvious reason to complete

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

    itch, since, fought, contradicts

    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
    0.64
    御座
    0.48
    作った
    0.46
    heated
    0.45
    sorry
    0.45
     fined
    0.44
    れ
    0.44
     dilated
    0.42
    ຫ
    0.42
    table
    0.42
    POSITIVE LOGITS
    PlatformImage
    0.53
     rechts
    0.52
     imprend
    0.51
    AttrName
    0.51
     financiers
    0.49
     potenciales
    0.49
     vínculo
    0.49
    ImageAsset
    0.48
     aplicativos
    0.48
     afuera
    0.48
    Activations Density 0.003%

    No Known Activations