© 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. 241650
    Prev
    Next
    INDEX
    Explanations

    eyes closed or blind

    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
    髌
    0.52
     المياه
    0.50
    漣
    0.50
     قلي
    0.49
     জলের
    0.48
     saudável
    0.46
     мони
    0.46
     saludable
    0.45
     забезпе
    0.45
     ውሃ
    0.45
    POSITIVE LOGITS
     blind
    1.05
     Blind
    1.04
    Blind
    0.98
    blind
    0.95
    盲
    0.89
     blindness
    0.79
     blindly
    0.70
     blinded
    0.70
     ब्लाइंड
    0.65
     blinds
    0.61
    Activations Density 0.034%

    No Known Activations