© 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. 117606
    Prev
    Next
    INDEX
    Explanations

    fainting, unconsciousness, dizziness

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

    loss of consciousness and confusion

    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
     zerstört
    0.46
    龇
    0.45
     მშ
    0.45
     уничто
    0.42
     разру
    0.42
     destroy
    0.41
     oorlog
    0.41
    築
    0.41
    destructive
    0.41
     zerst
    0.41
    POSITIVE LOGITS
     fainting
    1.01
    晕
    0.84
     অচেতন
    0.78
     बेह
    0.72
     drows
    0.71
    昏
    0.71
     slumped
    0.71
     faint
    0.70
     unconscious
    0.64
     மய
    0.64
    Activations Density 0.097%

    No Known Activations