© 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. 109333
    Prev
    Next
    INDEX
    Explanations

    severe injuries

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

    priority

    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
    糁
    0.50
     chữa
    0.49
    ﹰ
    0.47
     ગામ
    0.47
    疳
    0.47
    発見
    0.46
    க்
    0.46
    ަކ
    0.46
     Восто
    0.45
    諡
    0.45
    POSITIVE LOGITS
     insurers
    0.52
     streamers
    0.49
    ’
    0.49
     footballers
    0.49
     DVR
    0.48
     huidige
    0.48
     progn
    0.47
     terminals
    0.46
     screenings
    0.46
     dirig
    0.46
    Activations Density 0.001%

    No Known Activations