© 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. 115059
    Prev
    Next
    INDEX
    Explanations

    your carpet

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

    sexuality and related concepts

    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
    зик
    0.47
    Jr
    0.47
    rik
    0.46
    перед
    0.44
     jr
    0.44
     evin
    0.44
    .
    0.43
    ?.
    0.43
     zde
    0.43
     vš
    0.42
    POSITIVE LOGITS
    戙
    0.55
     头
    0.52
    urètre
    0.49
    čnost
    0.48
    लॉक
    0.48
    kowej
    0.48
    ეთის
    0.47
    檤
    0.46
    铯
    0.46
     တယ်
    0.46
    Activations Density 0.001%

    No Known Activations