© 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. 21039
    Prev
    Next
    INDEX
    Explanations

    opioid overdose

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

    needed to maintain

    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
    ↵↵
    0.50
     â
    0.46
    ?
    0.46
    .
    0.42
     &
    0.42
     a
    0.40
    0.40
    agg
    0.39
     :
    0.39
    ρχ
    0.39
    POSITIVE LOGITS
    getBlueTeam
    0.49
    جموع
    0.48
    ূন্য
    0.47
     एक्सरसा
    0.46
     पूर्वानु
    0.45
    یرو
    0.44
     خلاص
    0.43
     سلمان
    0.43
    枴
    0.43
     اهم
    0.43
    Activations Density 0.000%

    No Known Activations