© 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. 134025
    Prev
    Next
    INDEX
    Explanations

    Northern Asia; categories; exceptions

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

    esp, EX, exactly

    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
    auz
    0.43
     hof
    0.40
    மைக்
    0.38
     tabi
    0.38
     యే
    0.38
    osit
    0.37
     حسب
    0.37
    閏
    0.37
    とし
    0.37
    __'
    0.36
    POSITIVE LOGITS
     Exodus
    0.45
     Esp
    0.45
     E
    0.43
     Française
    0.42
    EX
    0.41
     Empres
    0.41
    ⢸
    0.41
     designation
    0.40
    Exception
    0.40
     Exit
    0.40
    Activations Density 0.066%

    No Known Activations