© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20087
    Prev
    Next
    INDEX
    Explanations

    statistics and relationships

    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
    ยาก
    0.43
     jederzeit
    0.43
     นอกจาก
    0.42
    कई
    0.40
     है
    0.39
    Inj
    0.39
     musí
    0.39
    靛
    0.38
    ለው
    0.37
     exasper
    0.37
    POSITIVE LOGITS
    posites
    0.45
     RCLCPP
    0.44
     communal
    0.42
     defined
    0.41
    isdigit
    0.41
    unistd
    0.41
     নিবাস
    0.40
     comunicado
    0.40
     شدم
    0.40
     dedim
    0.40
    Activations Density 0.018%

    No Known Activations