© 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. 33316
    Prev
    Next
    INDEX
    Explanations

    buying or purchasing

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

    buying or selling acts

    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
    스
    0.79
    لین
    0.75
    ה
    0.73
    اک
    0.73
    ク
    0.72
    DATA
    0.70
    বারের
    0.70
    プリント
    0.69
    За
    0.69
    な
    0.68
    POSITIVE LOGITS
    ari
    0.67
    ät
    0.67
    able
    0.65
    omer
    0.64
    ни
    0.64
    ough
    0.63
    ère
    0.61
    ความ
    0.60
     buy
    0.59
    in
    0.59
    Activations Density 0.069%

    No Known Activations