© 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. 203580
    Prev
    Next
    INDEX
    Explanations

    ; followed by Locate, Option, Select

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

    garlic bread, eating contest, owned

    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
    ञ्च
    0.57
    کر
    0.52
    Liên
    0.48
     جیسے
    0.48
    バ
    0.47
    Č
    0.47
    糺
    0.47
    WE
    0.47
    Лі
    0.47
    りで
    0.46
    POSITIVE LOGITS
    ya
    0.53
    rae
    0.48
     Champaign
    0.46
     Rolle
    0.45
     Godfather
    0.44
    issimo
    0.43
    inator
    0.43
     Sixth
    0.43
     Tun
    0.42
     कहीं
    0.42
    Activations Density 0.000%

    No Known Activations