© 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. 182521
    Prev
    Next
    INDEX
    Explanations

    digits and citations

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

    multiple choice answers

    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
     knife
    0.44
    Una
    0.40
    xlink
    0.40
    カテゴ
    0.38
    썸
    0.38
    Catch
    0.38
     hsl
    0.37
     컨
    0.37
     Una
    0.37
     catch
    0.36
    POSITIVE LOGITS
     цю
    0.45
    ామ
    0.44
     Гинд
    0.43
    nemis
    0.42
    詿
    0.41
    ಾರದ
    0.40
     পিত
    0.38
    ары
    0.38
     Argy
    0.38
    amay
    0.38
    Activations Density 0.002%

    No Known Activations