© 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. 138818
    Prev
    Next
    INDEX
    Explanations

    names, things, and places

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

    business terms

    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
    તુ
    0.53
    包人
    0.51
    ী
    0.50
     Strukt
    0.49
    ش
    0.48
    ிய
    0.47
    AndDelete
    0.47
    ल
    0.47
     આવેલા
    0.47
    Elater
    0.47
    POSITIVE LOGITS
     vocal
    0.52
     rhythms
    0.51
     pat
    0.50
    ats
    0.50
     acumen
    0.49
      
    0.48
     oils
    0.48
     notations
    0.47
     intelligence
    0.47
     taco
    0.47
    Activations Density 0.000%

    No Known Activations