© 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. 241064
    Prev
    Next
    INDEX
    Explanations

    LL Bean

    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
    HORIZONTAL
    0.46
     向
    0.46
    şehir
    0.45
     конфи
    0.44
     شهری
    0.44
     भक्त
    0.44
    équip
    0.44
    ﹕
    0.43
     限
    0.42
     なかっ
    0.42
    POSITIVE LOGITS
     by
    0.48
     alcune
    0.48
     ostat
    0.46
     noget
    0.46
     marks
    0.45
     cannabinoids
    0.44
     staffing
    0.43
     reactions
    0.43
     earnings
    0.43
     outra
    0.43
    Activations Density 0.000%

    No Known Activations