© 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. 157875
    Prev
    Next
    INDEX
    Explanations

    hear all

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

    '(', 'work', 'oiled', 'high', 'if', 'to'

    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
     liên
    0.53
    जिए
    0.48
     ιστο
    0.47
     overtime
    0.46
     ισ
    0.45
    粎
    0.45
     три
    0.43
    multipart
    0.43
     ढांचे
    0.43
     CONSULT
    0.43
    POSITIVE LOGITS
    ’
    0.50
     فاض
    0.45
    ׳
    0.45
    함으로써
    0.42
    לט
    0.42
     Entsche
    0.40
    ´
    0.40
    lé
    0.39
     decreed
    0.39
    prochen
    0.39
    Activations Density 0.000%

    No Known Activations