© 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. 206432
    Prev
    Next
    INDEX
    Explanations

    legal, biological, and financial terms

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

    footjob

    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
     baryons
    0.48
     SINGH
    0.48
     basses
    0.48
    :
    0.47
     $[\
    0.46
     numele
    0.45
     necessaria
    0.44
     mandates
    0.44
     seta
    0.44
     basilaires
    0.44
    POSITIVE LOGITS
     മെ
    0.47
    おお
    0.47
     فات
    0.46
     먼
    0.45
    軀
    0.45
    口コミ
    0.45
    wide
    0.44
     Wie
    0.44
    पीड़न
    0.44
    wie
    0.44
    Activations Density 0.000%

    No Known Activations