© 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. 224661
    Prev
    Next
    INDEX
    Explanations

    proposals . best

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

    Central areas, add segments

    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
    _
    0.51
     milliliters
    0.48
    東
    0.44
    ス
    0.44
     東
    0.43
    つつ
    0.43
     マット
    0.41
     dimerization
    0.40
     railroad
    0.40
    陳
    0.40
    POSITIVE LOGITS
     Система
    0.56
     наз
    0.46
     системой
    0.46
    గ్రహ
    0.46
     deres
    0.46
    嚨
    0.46
     adaptarse
    0.46
    ándose
    0.45
    larına
    0.45
    ड्रीम
    0.45
    Activations Density 0.001%

    No Known Activations