© 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. 149468
    Prev
    Next
    INDEX
    Explanations

    commerce, business transactions, and specific entities

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

    floating point

    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
    镙
    0.52
    Channels
    0.47
    营
    0.47
    ている
    0.46
    ត្ត
    0.46
    铐
    0.46
    થ
    0.46
    倌
    0.46
     बगल
    0.45
     confusión
    0.44
    POSITIVE LOGITS
     D
    0.57
     R
    0.55
     CON
    0.53
    </h3>
    0.52
     Ottawa
    0.48
    oons
    0.48
    </strong>
    0.48
     =
    0.47
     E
    0.46
     sederhana
    0.46
    Activations Density 0.000%

    No Known Activations