© 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. 175165
    Prev
    Next
    INDEX
    Explanations

    business and economics

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

    survival, impairments, invasive, sensory

    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
    탑
    0.50
    야
    0.50
    ".
    0.48
    境界
    0.48
    صل
    0.47
    "،
    0.47
    刧
    0.45
    ΰ
    0.44
     असता
    0.43
    '
    0.43
    POSITIVE LOGITS
     creeps
    0.50
     interviewed
    0.48
     outcast
    0.48
     inhaled
    0.48
     laborers
    0.47
    ন্দ্ব
    0.47
     einzigen
    0.47
     जिनसे
    0.47
     chemicals
    0.46
     deformations
    0.46
    Activations Density 0.001%

    No Known Activations