© 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. 22-GEMMASCOPE-RES-131K
    4. 11440
    Prev
    Next
    INDEX
    Explanations

    lists, menus, and specific evaluations

    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
    んでいます
    -1.71
    んでる
    -1.69
     ребё
    -1.61
     pueden
    -1.42
     didn
    -1.34
    깐
    -1.34
     don
    -1.33
     puedes
    -1.31
     America
    -1.30
     bañera
    -1.30
    POSITIVE LOGITS
    暧
    1.74
     ideia
    1.57
     túnel
    1.55
    至尊
    1.48
     CRUZ
    1.48
    ᾽
    1.41
    Commenting
    1.38
    𓂂
    1.33
     fórmula
    1.32
    Asimismo
    1.32
    Activations Density 0.010%

    No Known Activations