© 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. 36452
    Prev
    Next
    INDEX
    Explanations

    line make

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

    Raw Materials

    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
    (
    0.52
    해서
    0.50
    hai
    0.48
     ailments
    0.47
    ific
    0.46
     at
    0.46
     frictions
    0.44
    iglia
    0.43
    Ses
    0.43
    ou
    0.43
    POSITIVE LOGITS
    лександр
    0.49
     సాహిత్య
    0.49
     แอ
    0.48
    yacute
    0.48
     Й
    0.48
    IVATE
    0.48
     Akk
    0.48
     INumber
    0.47
     Лю
    0.47
     बीटल
    0.47
    Activations Density 0.000%

    No Known Activations