© 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. 182788
    Prev
    Next
    INDEX
    Explanations

    college campus

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

    foot fetish stories

    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
    opies
    0.48
    轨
    0.48
     Racial
    0.46
    iges
    0.45
    ático
    0.44
    erts
    0.44
     गाड़ी
    0.43
    igy
    0.43
    轨迹
    0.43
    狂
    0.42
    POSITIVE LOGITS
     vote
    0.52
     businesswoman
    0.52
     financing
    0.50
     partner
    0.50
     confiance
    0.49
     shopper
    0.47
     tombol
    0.46
     sendMessage
    0.46
     businessman
    0.45
     NUS
    0.45
    Activations Density 0.001%

    No Known Activations