© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 184326
    Prev
    Next
    INDEX
    Explanations

    rights and privacy

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

    privacy and surveillance

    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
    އ
    0.53
    лено
    0.50
     produzido
    0.50
     magical
    0.50
    aaf
    0.50
    დება
    0.49
    然后再
    0.49
    detalle
    0.47
     earrings
    0.46
     ლ
    0.46
    POSITIVE LOGITS
    Extent
    0.52
    ü
    0.47
    KeyState
    0.46
     مهر
    0.44
    Header
    0.44
    MaxValue
    0.44
     APIs
    0.44
     वॉइस
    0.44
    伷
    0.43
     Fäh
    0.43
    Activations Density 0.000%

    No Known Activations