© 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. 23413
    Prev
    Next
    INDEX
    Explanations

    technological acceleration

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

    specific sequences follow certain words

    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
    iguity
    0.51
    itie
    0.47
     sensibilité
    0.46
    fold
    0.46
    ard
    0.46
    diethyl
    0.45
     தாக்க
    0.45
    険
    0.44
    oitte
    0.44
     場合
    0.44
    POSITIVE LOGITS
     lags
    0.52
     lidar
    0.49
     rosas
    0.49
     lindos
    0.49
     stadion
    0.47
    ხმარ
    0.47
     silt
    0.47
     cars
    0.46
    崞
    0.46
     geot
    0.46
    Activations Density 0.000%

    No Known Activations