© 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. 12341
    Prev
    Next
    INDEX
    Explanations

    common statements by people

    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
    <td>
    -1.05
    らなかった
    -1.00
     bey
    -0.99
    haped
    -0.98
     from
    -0.98
    Etter
    -0.97
    "}}>
    -0.97
    ;</
    -0.97
    érrez
    -0.96
    谜
    -0.95
    POSITIVE LOGITS
     often
    1.46
    often
    1.27
    Often
    1.22
     sometimes
    1.16
     saying
    1.16
     many
    1.08
     ২০১
    1.07
    Sometimes
    1.06
     said
    1.05
     souvent
    1.04
    Activations Density 0.091%

    No Known Activations