© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 55139
    Prev
    Next
    INDEX
    Explanations

    you want / human has

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

    timeless beauty

    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
     drugg
    0.48
     emission
    0.47
     epoca
    0.47
     autonomia
    0.45
     ahi
    0.44
     ㅏ
    0.44
     anno
    0.44
     ehm
    0.43
     pią
    0.43
     会
    0.43
    POSITIVE LOGITS
    茯
    0.50
     liệu
    0.46
    theory
    0.45
    crystalline
    0.45
    PreviewSize
    0.45
    aw
    0.43
     понял
    0.43
     लोक
    0.43
     ঘটতে
    0.43
    iferous
    0.42
    Activations Density 0.000%

    No Known Activations