© 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. 79237
    Prev
    Next
    INDEX
    Explanations

    tech at, sheets while, operated cam, team in

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

    communication and actions

    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
    Alla
    0.50
     заклю
    0.50
    Ala
    0.48
    𝑭
    0.46
    쟌
    0.46
    Abraham
    0.45
     }]);
    0.45
    Those
    0.45
    Zara
    0.44
    참
    0.44
    POSITIVE LOGITS
    ية
    0.54
    بية
    0.53
     warden
    0.50
    t
    0.48
     vés
    0.47
     gegeben
    0.47
    園
    0.46
     marker
    0.45
     Hels
    0.45
    uración
    0.43
    Activations Density 0.001%

    No Known Activations