© 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. 156594
    Prev
    Next
    INDEX
    Explanations

    made/produced in context

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

    language predicting response

    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
     P
    0.46
     Courtney
    0.43
     Sally
    0.42
     Tom
    0.42
     Ps
    0.42
     Virginia
    0.42
     skj
    0.42
     mockery
    0.42
    ्याम
    0.41
    䛊
    0.41
    POSITIVE LOGITS
     gamepad
    0.47
     tetromino
    0.45
    ници
    0.44
    chatroom
    0.43
    SERVICES
    0.43
    stringValue
    0.43
    clientWidth
    0.43
    CategoryImage
    0.42
     diversify
    0.42
    ROLE
    0.42
    Activations Density 0.001%

    No Known Activations