© 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-262K
    7. 4090
    Prev
    Next
    INDEX
    Explanations

    foreign keys 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_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
     leisten
    0.53
     merciful
    0.52
     intraven
    0.50
     pyrolysis
    0.50
    positroid
    0.49
    ucksack
    0.49
    keletal
    0.48
    🩹
    0.48
    ıç
    0.48
     reformulated
    0.48
    POSITIVE LOGITS
     relation
    0.77
     relationship
    0.76
     association
    0.71
     associate
    0.71
    relation
    0.70
    Relation
    0.70
     associating
    0.69
    关联
    0.68
     Relation
    0.64
     Relationship
    0.64
    Activations Density 0.171%

    No Known Activations