© 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. 26543
    Prev
    Next
    INDEX
    Explanations

    market, passage, foreign names

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

    letterhead structure analyses

    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
    "
    0.57
    Q
    0.52
    dump
    0.48
    ¿
    0.47
    Д
    0.46
    щност
    0.46
    days
    0.46
    fundamentals
    0.46
    tool
    0.44
    Ο
    0.44
    POSITIVE LOGITS
     Aachen
    0.53
    𒈦
    0.53
     المسي
    0.51
    acrylate
    0.51
     parques
    0.51
     väč
    0.50
     Âu
    0.50
     العاش
    0.50
     Biele
    0.50
     slučaj
    0.50
    Activations Density 0.000%

    No Known Activations