© 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-65K
    4. 2910
    Prev
    Next
    INDEX
    Explanations

    social, technical, or conceptual entities

    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_65k_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
    G
    0.45
     embed
    0.45
     embedding
    0.45
     obsess
    0.45
     others
    0.43
     auditor
    0.43
     PEACE
    0.42
     exporting
    0.42
     korean
    0.42
     encoding
    0.41
    POSITIVE LOGITS
    aktif
    0.46
    ཝ
    0.46
     تشخیص
    0.46
     Waste
    0.45
     Зу
    0.45
     Mist
    0.45
     वाचा
    0.43
     فط
    0.43
    㝌
    0.42
    苻
    0.42
    Activations Density 0.010%

    No Known Activations