© 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. 203105
    Prev
    Next
    INDEX
    Explanations

    million cubic

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

    games played

    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
     acredito
    0.46
    坦
    0.46
    ారి
    0.45
     usb
    0.43
     itulah
    0.43
     quirks
    0.42
     reseller
    0.42
    ेंग
    0.42
     muzzle
    0.42
     makeup
    0.42
    POSITIVE LOGITS
    ໃນ
    0.54
    ladı
    0.53
    یکا
    0.50
    Brom
    0.50
    ஸ
    0.50
     ایک
    0.48
    후
    0.48
    ignés
    0.48
    Під
    0.47
    வது
    0.47
    Activations Density 0.000%

    No Known Activations