© 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. 35331
    Prev
    Next
    INDEX
    Explanations

    not drinking, have excellent, until December

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

    specific entities

    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
    启
    0.49
    로
    0.48
    倌
    0.48
    琢
    0.47
    泯
    0.47
    觊
    0.47
    沆
    0.46
    冀
    0.46
     Eats
    0.46
    략
    0.45
    POSITIVE LOGITS
     azienda
    0.52
     successively
    0.51
     kumar
    0.50
    <0x80>
    0.49
     periodicity
    0.47
     weer
    0.47
     practition
    0.46
     code
    0.46
     accreditation
    0.46
     atmosphere
    0.45
    Activations Density 0.000%

    No Known Activations