© 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. 44692
    Prev
    Next
    INDEX
    Explanations

    classification

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

    declarations, definitions, modules

    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
     sceGu
    0.53
     ಕಾಣ
    0.49
    電池
    0.44
    ¹.
    0.44
    деш
    0.44
    FFE
    0.44
    怦
    0.44
    ઞ
    0.43
    REET
    0.43
     signify
    0.43
    POSITIVE LOGITS
     প্রতিহিংস
    0.51
    s
    0.44
     nuova
    0.44
    udent
    0.41
     Molecular
    0.41
     rostro
    0.40
     প্রতিশোধ
    0.40
    绣
    0.40
    romagnet
    0.39
     ক্লাস
    0.39
    Activations Density 0.000%

    No Known Activations