© 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. 235969
    Prev
    Next
    INDEX
    Explanations

    mg/ml topical

    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
    ды
    0.52
    дом
    0.46
    ද්ධ
    0.46
    バシー
    0.46
    Gé
    0.46
    getDoctrine
    0.45
    á
    0.44
    గల
    0.44
     voces
    0.44
    ご理解
    0.44
    POSITIVE LOGITS
     suboptimal
    0.52
     带
    0.50
     代码
    0.48
     예를
    0.47
     माणसा
    0.46
     까지
    0.45
     aft
    0.45
    但是
    0.45
     Relating
    0.45
     但是
    0.44
    Activations Density 0.000%

    No Known Activations