© 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. 251452
    Prev
    Next
    INDEX
    Explanations

    quantifiable outcomes or descriptions

    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
    ges
    0.53
    aulay
    0.52
    un
    0.51
    gings
    0.47
    dan
    0.47
    i
    0.47
    cn
    0.47
    watering
    0.47
    la
    0.46
    ga
    0.46
    POSITIVE LOGITS
     ime
    0.57
     MSC
    0.56
     cabo
    0.54
     ザ
    0.51
     ră
    0.50
     diretor
    0.50
     Tirol
    0.50
     沖縄
    0.50
     時間
    0.49
     Volt
    0.49
    Activations Density 0.004%

    No Known Activations