© 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. 115858
    Prev
    Next
    INDEX
    Explanations

    question marks and URLs

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

    questions and foreign punctuation

    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
    ことです
    0.47
     abstractions
    0.46
     Databases
    0.42
     abstra
    0.40
     Pohl
    0.39
    --',
    0.39
     ME
    0.39
    ifo
    0.39
    生气
    0.39
     Bertram
    0.39
    POSITIVE LOGITS
     ؟
    0.57
     ?”
    0.54
    ؟
    0.53
    ?”
    0.52
    ؟؟
    0.52
    ؟!
    0.52
    ?”
    0.51
     ?
    0.51
     ?)
    0.51
    ?
    0.51
    Activations Density 0.000%

    No Known Activations