© 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. 118661
    Prev
    Next
    INDEX
    Explanations

    final project completion

    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
     آزمون
    -0.82
     Fod
    -0.77
     关闭
    -0.74
    GPT
    -0.73
    缂
    -0.73
     Vitamina
    -0.73
     デニム
    -0.72
     invitations
    -0.72
    Repair
    -0.72
     SqlConnection
    -0.72
    POSITIVE LOGITS
     project
    3.06
     cap
    2.69
     final
    2.58
     Cap
    2.38
    Cap
    2.34
     Final
    2.33
     projects
    2.23
    Final
    2.23
    project
    2.22
    final
    2.17
    Activations Density 0.070%

    No Known Activations