© 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. 34-GEMMASCOPE-RES-131K
    7. 118933
    Prev
    Next
    INDEX
    Explanations

    legal notices or licenses

    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_34/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
    呼ぶ
    -0.84
    ধ
    -0.79
     books
    -0.79
     للم
    -0.77
    前来
    -0.76
    かを
    -0.76
    場合には
    -0.76
     للت
    -0.75
     треба
    -0.74
    ماً
    -0.73
    POSITIVE LOGITS
     logo
    1.10
     parcial
    1.01
     Logo
    1.01
    Logo
    0.97
    logo
    0.93
     ISSN
    0.89
    flasche
    0.85
    LOGO
    0.84
    kú
    0.84
     logos
    0.81
    Activations Density 0.002%

    No Known Activations