© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147931
    Prev
    Next
    INDEX
    Explanations

    Neo4j cypher queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     tables
    0.87
     table
    0.83
     kuba
    0.80
     FPS
    0.77
     iframe
    0.77
    蔗
    0.76
    nahi
    0.73
    琨
    0.72
     Table
    0.72
    table
    0.72
    POSITIVE LOGITS
    ак
    0.67
     לפ
    0.64
    क्ल
    0.62
    eurs
    0.61
     מ
    0.60
    php
    0.59
    Bolt
    0.59
    塾
    0.58
     ב
    0.58
     garante
    0.57
    Activations Density 0.003%

    No Known Activations