© 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. 48273
    Prev
    Next
    INDEX
    Explanations

    company name screening

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

    disclosure or categories

    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
     زمان
    0.51
    मंदिर
    0.51
    馇
    0.51
     내가
    0.50
     timpul
    0.49
    আমার
    0.49
    IOR
    0.46
     ابنائي
    0.46
     उत्पत्ति
    0.46
    Ftp
    0.46
    POSITIVE LOGITS
     schoon
    0.50
     Cleanup
    0.48
    褪
    0.46
     disclosure
    0.46
     disclosed
    0.46
     landowners
    0.46
     cleanup
    0.45
     Flücht
    0.45
    eroy
    0.45
     відпо
    0.44
    Activations Density 0.000%

    No Known Activations