© 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. 10-GEMMASCOPE-RES-131K
    7. 735
    Prev
    Next
    INDEX
    Explanations

    glossy finish

    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_10/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>
    -1.38
     would
    -1.35
     in
    -1.32
     indivíduo
    -1.28
    givers
    -1.27
     was
    -1.26
     of
    -1.23
     based
    -1.20
    ocios
    -1.19
    却又
    -1.19
    POSITIVE LOGITS
    '
    1.57
    车型
    1.43
     sheen
    1.36
    時間の
    1.35
     später
    1.34
     rutas
    1.30
    了我
    1.24
    Generally
    1.24
    {
    1.23
    There
    1.23
    Activations Density 0.037%

    No Known Activations