© 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. 195736
    Prev
    Next
    INDEX
    Explanations

    American audio/video content

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

    various technical and specific terms

    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
     perverse
    0.49
     warped
    0.48
    вались
    0.46
     marriages
    0.46
     restit
    0.45
    ь
    0.45
    ياته
    0.45
     inmobili
    0.45
    ጥነት
    0.45
     sensitized
    0.45
    POSITIVE LOGITS
    Interactive
    0.53
     मुस्
    0.49
     Audiobook
    0.47
    Dropdown
    0.46
    Video
    0.46
     সেরা
    0.46
    🅐
    0.46
    dropdown
    0.45
    saxophone
    0.45
     লিঙ্ক
    0.45
    Activations Density 0.000%

    No Known Activations