© 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. 209756
    Prev
    Next
    INDEX
    Explanations

    discussing prices or sales

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

    implies or clarifies intent

    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
    所
    0.47
    特别是
    0.44
    Са
    0.44
    盒
    0.43
    计算机
    0.41
     ремо
    0.41
    ます
    0.41
    阈
    0.41
    TA
    0.41
    METAL
    0.40
    POSITIVE LOGITS
     mourn
    0.53
     Congressional
    0.50
     anniversary
    0.48
     hysterical
    0.48
     congressman
    0.47
     hysteria
    0.47
    otest
    0.46
     affidavit
    0.45
     Nashville
    0.45
     süd
    0.45
    Activations Density 0.000%

    No Known Activations