© 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. 116666
    Prev
    Next
    INDEX
    Explanations

    map below, book online

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

    monitor closely; parts granulated; pond applications

    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
     रन
    0.52
    her
    0.49
     spiller
    0.48
    š
    0.46
    orbid
    0.46
     श्रॉफ
    0.44
    ш
    0.44
    ले
    0.44
    escent
    0.44
    acionales
    0.43
    POSITIVE LOGITS
     Kanpur
    0.46
     Kxc
    0.46
     appease
    0.46
     Examine
    0.46
     Hangzhou
    0.46
     多い
    0.45
     Gia
    0.45
     vân
    0.45
    :
    0.45
     Pyongyang
    0.44
    Activations Density 0.001%

    No Known Activations