© 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. 109468
    Prev
    Next
    INDEX
    Explanations

    medical and legal consultations

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

    Adding, Building, Construction

    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
     adjectives
    0.57
     ਨ
    0.51
     ડ
    0.50
     ਕ
    0.48
     Hersteller
    0.48
     tradu
    0.47
     illusions
    0.47
    umptions
    0.46
     Autobi
    0.46
     exclaimed
    0.46
    POSITIVE LOGITS
    e
    0.48
    iamiento
    0.48
    之外
    0.47
    删除
    0.46
    一对
    0.44
    舫
    0.44
    出
    0.44
     anteriormente
    0.44
    辑
    0.43
     completamente
    0.42
    Activations Density 0.001%

    No Known Activations