© 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. 114880
    Prev
    Next
    INDEX
    Explanations

    web sites

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

    bikers, sexual activity, cat photos, email, server

    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
    0
    0.57
     ム
    0.46
    abilities
    0.43
    hips
    0.43
     人
    0.43
    c
    0.42
    MR
    0.42
    PR
    0.42
    ível
    0.42
    osov
    0.42
    POSITIVE LOGITS
     اولمپس
    0.52
    landı
    0.46
    𝗙
    0.46
     flesh
    0.46
     дослі
    0.45
     furtherance
    0.44
    ıştı
    0.43
    𝘷
    0.43
    തു
    0.43
    ानंद
    0.43
    Activations Density 0.001%

    No Known Activations