© 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. 169535
    Prev
    Next
    INDEX
    Explanations

    hearing loss

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

    gain perspective and context

    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
    ms
    0.52
    ْم
    0.50
    ق
    0.48
    of
    0.48
    ford
    0.47
    ching
    0.46
    iest
    0.46
    iness
    0.45
    ing
    0.45
    즈
    0.45
    POSITIVE LOGITS
     nü
    0.47
     factorización
    0.46
     Wessex
    0.46
     mydict
    0.44
     WIS
    0.43
    Tocco
    0.43
    ContextHeader
    0.43
    ሃኒ
    0.43
     neutrophils
    0.43
     asociada
    0.43
    Activations Density 0.002%

    No Known Activations