© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178433
    Prev
    Next
    INDEX
    Explanations

    on-ball screen

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

    listing concepts, causes, considerations

    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
    Negative Logits
    მა
    0.49
    це
    0.48
    قط
    0.48
    umbia
    0.48
    То
    0.46
    })=\
    0.46
    Cedar
    0.46
    为
    0.45
    Ken
    0.45
    Pipe
    0.44
    POSITIVE LOGITS
     prvi
    0.45
     requisito
    0.45
     τησ
    0.45
     Sear
    0.44
     ahuv
    0.44
     indices
    0.43
    jhelp
    0.43
     globale
    0.43
     crispy
    0.43
     chipset
    0.43
    Activations Density 0.000%

    No Known Activations