© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 38981
    Prev
    Next
    INDEX
    Explanations

    identification and authentication documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     músicas
    0.45
    규모
    0.42
    🎳
    0.41
    LogRow
    0.41
    䥑
    0.40
     emocionante
    0.40
     programación
    0.40
    টিত
    0.40
     丨
    0.39
     düşün
    0.39
    POSITIVE LOGITS
     인증
    0.77
     authentication
    0.75
     certificate
    0.75
    identification
    0.72
    认证
    0.71
     verification
    0.71
     Authentication
    0.71
     certificates
    0.70
     Certificate
    0.69
     certifying
    0.68
    Activations Density 0.066%

    No Known Activations