© 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. 99000
    Prev
    Next
    INDEX
    Explanations

    responsibility starts

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

    BITCH

    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
     hepatitis
    0.53
     custod
    0.51
    肪
    0.51
     activo
    0.50
     opulent
    0.49
     admirably
    0.49
     waxed
    0.48
     watery
    0.48
    সংখ্য
    0.48
     enorme
    0.48
    POSITIVE LOGITS
     இன்ற
    0.49
    Best
    0.45
     נמצא
    0.44
     ഞങ്ങൾ
    0.44
    ိုလ်
    0.44
    Nik
    0.43
    ("${
    0.43
     Kedua
    0.43
    second
    0.43
    ഒരു
    0.43
    Activations Density 0.000%

    No Known Activations