© 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. 83923
    Prev
    Next
    INDEX
    Explanations

    standards, appraisal, data

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

    data and evaluation

    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
     Эти
    0.60
     CaCl
    0.54
    ^{+}(
    0.48
     المالية
    0.48
     Rechte
    0.47
    nání
    0.46
     ArrayIndex
    0.45
     ficando
    0.45
    餚
    0.45
     Ř
    0.45
    POSITIVE LOGITS
    データ
    0.55
     appraisal
    0.50
    <
    0.50
    データを
    0.47
     précédentes
    0.47
    […]
    0.45
    hens
    0.44
    闺
    0.44
     평가
    0.44
    [...]
    0.43
    Activations Density 0.000%

    No Known Activations