© 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. 158375
    Prev
    Next
    INDEX
    Explanations

    then sections Ray ID output family thermal publish kept

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

    quotes and data lists

    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
     पौधा
    0.56
    ઙ
    0.53
    関東
    0.50
    asarray
    0.48
     ایش
    0.48
     드라마
    0.47
    چر
    0.47
     образ
    0.47
    jsdel
    0.46
     ຊ
    0.46
    POSITIVE LOGITS
    my
    0.48
    ">
    0.47
    -
    0.47
    “
    0.46
    "
    0.46
    ”
    0.45
    not
    0.45
    没有
    0.45
     widest
    0.43
     vera
    0.43
    Activations Density 0.000%

    No Known Activations