© 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. 71633
    Prev
    Next
    INDEX
    Explanations

    listingstoriesPDFtermsrequirement

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

    Operator, mom, liter

    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
    <0xA4>
    0.49
    فت
    0.46
    :
    0.44
     base
    0.41
    満
    0.41
    -
    0.41
    �
    0.41
    感动
    0.41
    *
    0.41
     communism
    0.40
    POSITIVE LOGITS
     বণ
    0.50
     кораб
    0.50
     വിൽപ്പന
    0.50
     বয়স্ক
    0.50
     বণিক
    0.49
    ാർ
    0.49
     څرنګوالی
    0.49
     ससु
    0.48
     considérée
    0.48
     disparu
    0.48
    Activations Density 0.000%

    No Known Activations