© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 776
    Prev
    Next
    INDEX
    Explanations

    JavaScript object definitions

    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
     will
    -1.71
     or
    -1.69
     it
    -1.29
    Descrição
    -1.27
     the
    -1.27
     ή
    -1.21
     etc
    -1.20
     antworte
    -1.19
    近年
    -1.18
     می‌کن
    -1.18
    POSITIVE LOGITS
    いましたが
    1.40
    他們的
    1.30
    并未
    1.30
    擷
    1.30
     a
    1.27
    ovým
    1.27
    身后的
    1.20
     Réponses
    1.20
    <bos>
    1.16
    倆
    1.16
    Activations Density 0.049%

    No Known Activations