© 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. 134459
    Prev
    Next
    INDEX
    Explanations

    US state locations

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

    US state abbreviations and names

    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
     Ось
    0.50
     Испании
    0.47
    Ⲃ
    0.46
     கிமு
    0.45
     პირადი
    0.45
     Mó
    0.44
    䣵
    0.44
     Grèce
    0.44
     കീ
    0.43
     යුතු
    0.43
    POSITIVE LOGITS
    भग
    0.46
    我们的
    0.46
     vores
    0.45
    ！
    0.45
    "
    0.45
    能
    0.44
     as
    0.42
    ων
    0.42
    我们可以
    0.42
     our
    0.41
    Activations Density 0.054%

    No Known Activations