© 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. 12651
    Prev
    Next
    INDEX
    Explanations

    shatter paper

    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
     всех
    0.52
    到现在
    0.50
    먼
    0.49
     yazd
    0.48
    靓
    0.47
    发的
    0.47
    だったので
    0.46
    рованной
    0.46
     نوشته
    0.46
     पाण्याच्या
    0.46
    POSITIVE LOGITS
    fas
    0.48
    noy
    0.47
    eliers
    0.47
    lovi
    0.47
    (=
    0.46
    ytes
    0.46
    fier
    0.46
    inct
    0.45
    ioxid
    0.45
    drig
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.