© 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. 131701
    Prev
    Next
    INDEX
    Explanations

    statements made by the producer

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

    drives libido and pleasure

    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
    倬
    0.50
    秃
    0.47
     Tracking
    0.47
     企业
    0.46
    荸
    0.46
    惩
    0.46
    به
    0.45
    跟踪
    0.45
    巴巴
    0.44
     वेडिंग
    0.44
    POSITIVE LOGITS
    overview
    0.50
    +{\
    0.47
    loft
    0.47
    fecha
    0.46
    Mercury
    0.46
    as
    0.44
    Oscar
    0.44
    feat
    0.44
    għ
    0.43
    round
    0.42
    Activations Density 0.000%

    No Known Activations