© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75895
    Prev
    Next
    INDEX
    Explanations

    tailored shirts

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

    Sexual content and communication methods

    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
    Negative Logits
    <0xF0>
    0.53
    ણ
    0.50
    多个
    0.49
     ডিপ
    0.48
     Tất
    0.48
    ̣
    0.48
     utilisant
    0.48
    茭
    0.47
    RawO
    0.47
    複数の
    0.47
    POSITIVE LOGITS
     murderous
    0.46
     remuneration
    0.46
     defamatory
    0.46
     pensioner
    0.45
     relegation
    0.44
     treason
    0.43
    payment
    0.43
     eventful
    0.43
     deceit
    0.43
     postcode
    0.42
    Activations Density 0.001%

    No Known Activations