© 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. 183865
    Prev
    Next
    INDEX
    Explanations

    showscurrentlifetrekkingfriend

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

    "Why" questions and explanations

    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
     پوائن
    0.48
     문제를
    0.46
     인사
    0.45
    앞
    0.44
    ocsát
    0.43
     проходить
    0.43
     오류
    0.42
     Ukraj
    0.42
    왼
    0.42
    IVEN
    0.42
    POSITIVE LOGITS
    pai
    0.44
    ’
    0.43
    ro
    0.43
     salts
    0.43
     Licht
    0.42
     microbes
    0.42
    csp
    0.42
    oli
    0.42
     nel
    0.42
     mais
    0.41
    Activations Density 0.001%

    No Known Activations