© 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. 248483
    Prev
    Next
    INDEX
    Explanations

    advice and requests

    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
    s
    0.48
    ant
    0.45
    Ref
    0.44
     signature
    0.43
    4
    0.43
     her
    0.42
     isotropic
    0.42
    re
    0.42
    ref
    0.42
     UE
    0.41
    POSITIVE LOGITS
     તપાસ
    0.50
     র‍
    0.50
     போட்ட
    0.48
     අනුව
    0.48
     shuts
    0.46
     ম্যানেজার
    0.45
    根據
    0.44
    等待
    0.44
     chromos
    0.43
     limitaciones
    0.43
    Activations Density 0.000%

    No Known Activations