© 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. 204763
    Prev
    Next
    INDEX
    Explanations

    uses Octopus

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

    real people, dial, year

    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
    -
    0.67
     Arctic
    0.49
     arctic
    0.48
     vehicles
    0.48
     superiority
    0.47
    "-
    0.46
    ya
    0.45
     tone
    0.45
     than
    0.44
     meters
    0.44
    POSITIVE LOGITS
    ओल
    0.60
     Fonbet
    0.50
    গতকাল
    0.50
    叄
    0.49
    asciiPanel
    0.49
    DeleteDialogOpen
    0.49
    हमारी
    0.48
    ARIOS
    0.48
    İL
    0.47
    LLA
    0.46
    Activations Density 0.001%

    No Known Activations