© 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. 68859
    Prev
    Next
    INDEX
    Explanations

    specifications and conditions

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

    relational model, NOT try, beyond individual schools

    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
    in
    0.55
    (
    0.53
    ”
    0.53
    useful
    0.52
     utiles
    0.49
    #
    0.47
     Middleware
    0.47
    ood
    0.46
    ington
    0.46
    幇
    0.46
    POSITIVE LOGITS
     může
    0.54
     начинает
    0.50
     скорость
    0.49
     религиоз
    0.49
     navigateur
    0.49
     опубликова
    0.48
     चैप्टर
    0.48
     może
    0.48
     sAlarm
    0.47
     kardeş
    0.47
    Activations Density 0.000%

    No Known Activations