© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100711
    Prev
    Next
    INDEX
    Explanations

    site graphics trailers

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

    unable to, seeing new, not a, Enabling:, HTTP(, safe vantage, not a, local sausages, for the, understand the

    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
    ING
    0.51
     电
    0.50
    ровкой
    0.48
    જનો
    0.47
     noviembre
    0.47
     taxon
    0.46
    梢
    0.46
     रखी
    0.45
    机场
    0.45
     Istituto
    0.45
    POSITIVE LOGITS
    ว่าง
    0.45
     평균
    0.45
    lical
    0.44
    ตุ
    0.44
     ਕੀਤਾ
    0.43
     
    0.43
    ทำ
    0.42
    ਕਾਰ
    0.42
    เฉ
    0.42
     اکن
    0.41
    Activations Density 0.000%

    No Known Activations