© 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. 129084
    Prev
    Next
    INDEX
    Explanations

    heart attack

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

    phrases formed by certain tokens

    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
    as
    0.55
     voila
    0.50
    ak
    0.49
    k
    0.49
     contas
    0.48
    ov
    0.47
    չ
    0.47
    щ
    0.47
    τσι
    0.46
     Catholics
    0.46
    POSITIVE LOGITS
    METAL
    0.53
    プレゼント
    0.50
    UInt
    0.46
     अने
    0.45
    pointe
    0.45
    ATE
    0.44
    Metal
    0.44
    FileLine
    0.44
    SDLCheck
    0.43
    BackgroundTask
    0.43
    Activations Density 0.000%

    No Known Activations