© 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. 181403
    Prev
    Next
    INDEX
    Explanations

    emissions come

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

    adjusting, integrating, and expanding

    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
    eld
    0.47
    প্রাচ
    0.42
    igno
    0.42
     മാത്ര
    0.41
     qualitative
    0.41
     produc
    0.41
     asin
    0.41
    ="#"><
    0.40
     produite
    0.40
    datab
    0.40
    POSITIVE LOGITS
    本日
    0.50
    Monday
    0.47
    ском
    0.46
    Д
    0.46
     incessantly
    0.46
    ్రహ్
    0.45
    Телефон
    0.45
    珍惜
    0.44
     frantically
    0.44
    Sunday
    0.43
    Activations Density 0.000%

    No Known Activations