© 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. 175459
    Prev
    Next
    INDEX
    Explanations

    basic setup

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

    not ... exclusively, entirely, about

    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
    كد
    0.45
     raro
    0.42
    spect
    0.42
    ндарт
    0.41
    лит
    0.40
     '['
    0.40
    compre
    0.40
     الول
    0.40
     MCD
    0.40
    <h6>
    0.40
    POSITIVE LOGITS
    Exclude
    0.55
     বেরিয়ে
    0.54
    entown
    0.50
    丆
    0.48
     اپنے
    0.46
    Constraints
    0.45
    گی
    0.45
     বিশ্লেষণ
    0.45
    Emoji
    0.44
     відбувається
    0.44
    Activations Density 0.000%

    No Known Activations