© 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. 72163
    Prev
    Next
    INDEX
    Explanations

    privacy statement

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

    Disks, variables, social, data, UUIDs

    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
     Looking
    0.55
    眈
    0.47
     Seorang
    0.47
     Turning
    0.46
    CONNECTED
    0.46
    んじゃない
    0.44
     beneficiary
    0.43
     So
    0.43
    একজন
    0.43
    璟
    0.43
    POSITIVE LOGITS
    userID
    0.53
    olded
    0.52
    familyName
    0.50
    nú
    0.48
    ού
    0.48
    lectricité
    0.48
    ute
    0.47
    ança
    0.46
    appi
    0.46
    Uuid
    0.45
    Activations Density 0.000%

    No Known Activations