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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 788
    Prev
    Next
    INDEX
    Explanations

    expressing hope for a future outcome

    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
    檮
    -1.76
    詳細は
    -1.69
    ......”
    -1.61
    </tfoot>
    -1.59
    ❗️
    -1.58
    $)$
    -1.52
    にします
    -1.52
    嘥
    -1.50
    D
    -1.50
    是怎么
    -1.49
    POSITIVE LOGITS
     According
    1.73
    蒾
    1.63
    枼
    1.59
    這個
    1.57
     which
    1.52
     of
    1.49
    y
    1.49
    at
    1.49
    戋
    1.49
     This
    1.48
    Activations Density 0.014%

    No Known Activations