© 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. 177946
    Prev
    Next
    INDEX
    Explanations

    complimentary tyre safety inspection

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

    roleplay, mistakes, and imitation

    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
    t
    0.47
    Kell
    0.46
     Kellogg
    0.45
     In
    0.44
    td
    0.44
     Cardano
    0.44
    day
    0.43
     Kek
    0.43
    In
    0.42
     Came
    0.42
    POSITIVE LOGITS
     മണ്ണി
    0.47
    韧
    0.46
     زمین
    0.46
     powied
    0.46
    ፈር
    0.45
    ‍♀️
    0.44
     მხ
    0.44
     канцеля
    0.44
    離島
    0.43
     fluency
    0.43
    Activations Density 0.000%

    No Known Activations