© 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. 243294
    Prev
    Next
    INDEX
    Explanations

    Mount followed by location

    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
    burden
    0.48
    vra
    0.48
    ////
    0.46
    付
    0.45
    بة
    0.45
    OI
    0.44
     crippling
    0.44
    <td>
    0.44
    倦
    0.44
    👻
    0.43
    POSITIVE LOGITS
     miest
    0.53
     étudier
    0.50
    নো
    0.49
     ات
    0.48
     Sonia
    0.48
     workspaces
    0.48
     nettoyer
    0.48
     avez
    0.47
     itinéraires
    0.47
     lütfen
    0.47
    Activations Density 0.000%

    No Known Activations