© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79091
    Prev
    Next
    INDEX
    Explanations

    mathematical interactions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     сзади
    -0.93
     باست
    -0.86
    assemble
    -0.85
    Haus
    -0.82
    🪧
    -0.81
    actual
    -0.81
     გ
    -0.79
    
    -0.79
    HAUS
    -0.79
    一方面
    -0.79
    POSITIVE LOGITS
     without
    0.85
     or
    0.83
     causing
    0.81
    preds
    0.80
    empêcher
    0.80
     showing
    0.79
     just
    0.79
    jątk
    0.77
     Wohnungen
    0.77
    mete
    0.75
    Activations Density 0.034%

    No Known Activations