© 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. 225637
    Prev
    Next
    INDEX
    Explanations

    standard and 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
    مني
    0.51
    நபியே
    0.45
    过多
    0.45
    FEM
    0.44
    јединачна
    0.43
    ברי
    0.42
     individuality
    0.41
    ();
    0.39
    рабаты
    0.39
    טע
    0.39
    POSITIVE LOGITS
     सरकारच्या
    0.63
     सप्टेंबर
    0.58
     फेब्रुवारी
    0.54
     आपल्या
    0.52
     예정
    0.52
     গিয়েছে
    0.52
     என்று
    0.51
     étaient
    0.51
     डिसेंबर
    0.51
     possèdent
    0.51
    Activations Density 0.000%

    No Known Activations