© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126672
    Prev
    Next
    INDEX
    Explanations

    vintage, resume, irish, polished, ocean, pics, weather

    np_acts-logits-general · gemini-2.5-flash-lite

    describes its operation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Centre
    0.69
     Advantage
    0.59
     Huan
    0.57
     Elk
    0.55
     Ko
    0.54
     Item
    0.54
     Olaf
    0.54
     M
    0.53
     Center
    0.53
     Lily
    0.53
    POSITIVE LOGITS
    똘
    0.48
    ق
    0.48
    عال
    0.47
     completos
    0.47
    િસ્
    0.46
    ប់
    0.46
    UnifiedTopology
    0.43
    ំប
    0.43
    されています
    0.43
    軍
    0.43
    Activations Density 0.004%

    No Known Activations