© 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. 131668
    Prev
    Next
    INDEX
    Explanations

    Factory with product

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

    scanner Day False Real

    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
     ショ
    0.51
     pravo
    0.51
     to
    0.51
     Ș
    0.50
     いっ
    0.48
     ક
    0.48
     Kč
    0.47
    هههه
    0.47
     capire
    0.46
     حیر
    0.46
    POSITIVE LOGITS
    Directions
    0.48
    Wings
    0.47
    呔
    0.46
    噵
    0.46
    閬
    0.45
     aerosols
    0.44
     Asians
    0.44
    ئات
    0.43
     Balloons
    0.43
     wanders
    0.43
    Activations Density 0.000%

    No Known Activations