© 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. 125183
    Prev
    Next
    INDEX
    Explanations

    implicit denial

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

    Whispering Tree, Woods, Pines

    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
     secondaires
    0.53
     ε
    0.52
     músc
    0.51
     Lucille
    0.50
     Δε
    0.48
     Oekra
    0.47
     Teich
    0.46
    િસ્
    0.46
     aé
    0.45
     unil
    0.45
    POSITIVE LOGITS
    N
    0.57
    тента
    0.54
    D
    0.54
    P
    0.51
    RAD
    0.49
    н
    0.49
    must
    0.49
    ном
    0.48
    MAC
    0.48
    Ave
    0.47
    Activations Density 0.000%

    No Known Activations