© 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. 36499
    Prev
    Next
    INDEX
    Explanations

    year ago or since

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

    1 unit

    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
    ۹
    0.72
    і
    0.63
    them
    0.61
    tiin
    0.61
    ৮
    0.60
    six
    0.59
    ণ
    0.59
    rza
    0.58
    ską
    0.57
    imizi
    0.56
    POSITIVE LOGITS
     of
    0.78
     for
    0.71
     with
    0.69
     ES
    0.63
     With
    0.61
     if
    0.61
     Experiments
    0.60
    1
    0.59
     On
    0.59
     By
    0.59
    Activations Density 0.030%

    No Known Activations