© 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. 250969
    Prev
    Next
    INDEX
    Explanations

    continued into configuration

    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
     tormented
    0.49
     plonge
    0.48
     imagines
    0.48
    臆
    0.47
     autorización
    0.46
     দাঁড়িয়ে
    0.46
    ského
    0.45
    autista
    0.45
     misguided
    0.45
     destrucción
    0.45
    POSITIVE LOGITS
     by
    0.60
    P
    0.58
    S
    0.57
    B
    0.57
     t
    0.54
    t
    0.53
    J
    0.52
    F
    0.51
    ены
    0.50
    U
    0.50
    Activations Density 0.000%

    No Known Activations