© 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. 12271
    Prev
    Next
    INDEX
    Explanations

    code structure

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

    formatting strings with variables

    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
     diá
    0.25
    섦
    0.25
     vudd
    0.24
     fün
    0.22
     və
    0.22
     culpa
    0.22
     anivers
    0.22
     tři
    0.22
     guérison
    0.21
     ermög
    0.21
    POSITIVE LOGITS
    s
    0.23
    ’
    0.22
    b
    0.22
    w
    0.21
    old
    0.20
    news
    0.19
    int
    0.19
    op
    0.19
    NS
    0.19
    writers
    0.19
    Activations Density 0.000%

    No Known Activations