© 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. 148147
    Prev
    Next
    INDEX
    Explanations

    famous Harvest Moon

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

    description, key, intercept, Party

    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
    R
    0.55
    u
    0.54
    A
    0.54
    am
    0.53
    Green
    0.53
    Sea
    0.52
    C
    0.52
    Sh
    0.51
    B
    0.51
    Gender
    0.51
    POSITIVE LOGITS
     suffit
    0.55
     suprem
    0.49
     irrepar
    0.48
     부족
    0.48
     mogą
    0.45
     favoriser
    0.45
     ಉತ್ಪನ್ನ
    0.45
     chercher
    0.44
     veineux
    0.44
     γνω
    0.44
    Activations Density 0.001%

    No Known Activations