© 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. 200381
    Prev
    Next
    INDEX
    Explanations

    making me, to request, for doctor

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

    components, operations, definitions

    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
     Hohen
    0.46
     г
    0.46
    immers
    0.46
    هما
    0.45
     Mehr
    0.45
     ਗ
    0.44
    stel
    0.44
    movied
    0.44
    reste
    0.43
     senare
    0.43
    POSITIVE LOGITS
     rộng
    0.49
    넓
    0.48
     Kiến
    0.48
    RDF
    0.47
    щем
    0.47
    ધ્ય
    0.46
    뀨
    0.46
    稳定的
    0.46
    વાડી
    0.46
    삑
    0.46
    Activations Density 0.000%

    No Known Activations