© 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-16K
    7. 12812
    Prev
    Next
    INDEX
    Explanations

    Nazar Lag

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

    sexual compatibility and intimate details

    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_16k_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
    ologischen
    0.54
     ぐらい
    0.50
    𝔬
    0.50
    文字列
    0.50
    उंस
    0.49
     чуть
    0.49
    设置
    0.48
    oš
    0.48
    ೮
    0.48
    ب
    0.48
    POSITIVE LOGITS
     Cyclone
    0.48
     Biden
    0.47
     FL
    0.44
     Biotechn
    0.43
     Ventures
    0.43
     Coastal
    0.43
     Han
    0.42
     Defendants
    0.42
     proje
    0.42
     peper
    0.42
    Activations Density 0.735%

    No Known Activations