© 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. 250939
    Prev
    Next
    INDEX
    Explanations

    locations, distributions, or specific entities

    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
    r
    0.55
    ne
    0.53
    ra
    0.52
    ang
    0.52
    FALL
    0.49
     سعی
    0.49
    FREQUENCY
    0.48
    ProgressListener
    0.47
    mdb
    0.47
    itali
    0.46
    POSITIVE LOGITS
    是可以
    0.45
    शियों
    0.45
     المل
    0.45
    大了
    0.45
    是要
    0.44
    們
    0.44
    க்கப்பட்ட
    0.44
     Bags
    0.44
     फाटक
    0.43
    繳
    0.43
    Activations Density 0.000%

    No Known Activations