© 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. 78940
    Prev
    Next
    INDEX
    Explanations

    US state and province abbreviations

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

    US states and cities

    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
    steak
    0.51
     দোকানে
    0.44
    resh
    0.42
    SELS
    0.40
    刷
    0.40
    hij
    0.40
    。
    0.40
    gcash
    0.39
    店
    0.39
     Amos
    0.39
    POSITIVE LOGITS
    ได้รับการ
    0.44
     bgColor
    0.42
    ור
    0.41
    พื้นที่
    0.41
     благодар
    0.41
     percib
    0.41
    แก้
    0.40
     управля
    0.40
     въз
    0.39
     hoàn
    0.39
    Activations Density 0.003%

    No Known Activations