© 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. 28398
    Prev
    Next
    INDEX
    Explanations

    multi-lingual text and formatting

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

    financial milestones

    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
     学生
    0.48
    োডে
    0.42
    {{\
    0.39
     className
    0.39
     паци
    0.39
    ോദ
    0.39
    ো
    0.38
    สัญญา
    0.38
     मुखिया
    0.37
     ENEM
    0.37
    POSITIVE LOGITS
     déclar
    0.46
    ওসি
    0.44
    पर्यंत
    0.42
     atrop
    0.41
     berharap
    0.40
     হই
    0.40
     ಅಧಿಕ
    0.39
     eucalyptus
    0.39
     électriques
    0.39
    崴
    0.39
    Activations Density 0.000%

    No Known Activations