© 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. 29489
    Prev
    Next
    INDEX
    Explanations

    events causing harm

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

    accident, trauma, or injury

    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
     Noida
    0.46
     إذ
    0.46
     Festivals
    0.45
     Optics
    0.45
     рит
    0.44
     উপমহাদেশ
    0.44
    噱
    0.44
     Markets
    0.43
    ଭ
    0.43
     সর্বত্র
    0.43
    POSITIVE LOGITS
     accident
    0.60
     pelvic
    0.59
     दुर्घटना
    0.58
     accidents
    0.55
     trauma
    0.54
    verlet
    0.53
     child
    0.52
     testicular
    0.52
     wounds
    0.51
     destructive
    0.51
    Activations Density 0.000%

    No Known Activations