© 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. 131787
    Prev
    Next
    INDEX
    Explanations

    What kind of procedures produce

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

    principle remains, flow of water, glows pale

    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
    ?
    0.47
     użytk
    0.46
     fácilmente
    0.46
     মানুষকে
    0.45
     ব্যবস্থা
    0.45
    érence
    0.45
    rás
    0.44
     굉장히
    0.43
    punkt
    0.42
    kepsilon
    0.42
    POSITIVE LOGITS
    र्की
    0.52
    立
    0.49
     owls
    0.48
    ேஷ்
    0.48
     aix
    0.47
    ាត
    0.47
    այի
    0.46
    َاب
    0.44
    登記
    0.44
    都
    0.43
    Activations Density 0.000%

    No Known Activations