© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12338
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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_22/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
     Introducción
    -0.97
     arrivent
    -0.94
     来自
    -0.93
     remporté
    -0.84
     這
    -0.84
     København
    -0.84
    theim
    -0.84
    在这个
    -0.83
     conferma
    -0.81
     überprüfen
    -0.81
    POSITIVE LOGITS
     such
    1.10
    <eos>
    1.08
     with
    0.95
     from
    0.95
    </h5>
    0.93
     so
    0.92
     an
    0.91
    用水
    0.89
     if
    0.89
     she
    0.87
    Activations Density 0.001%

    No Known Activations