© 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. 72484
    Prev
    Next
    INDEX
    Explanations

    Shepherd found, collected label, intrusion

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

    non-english words and origins

    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
     כא
    0.54
     וו
    0.52
     அமைக்க
    0.50
    瑉
    0.49
     ראש
    0.49
     গন
    0.48
     છો
    0.47
     מ
    0.47
     ಭಾರ
    0.47
     עד
    0.46
    POSITIVE LOGITS
    Originally
    0.47
    кто
    0.45
    ные
    0.44
    рун
    0.43
     originalmente
    0.43
    utako
    0.43
    țiuni
    0.42
    intrusion
    0.42
     originally
    0.40
    لها
    0.40
    Activations Density 0.000%

    No Known Activations