© 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. 108716
    Prev
    Next
    INDEX
    Explanations

    editing content or service

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

    adjust things; shifted weight; noticed his; marketed free; adjusted another; requires swap; patch Barn

    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
     insecticide
    0.49
     crash
    0.46
     angr
    0.44
     addr
    0.43
    IGR
    0.42
    .[/
    0.42
    AAAAAAAAAAAAAAAA
    0.42
    хо
    0.41
    ../
    0.41
    磴
    0.41
    POSITIVE LOGITS
    治療
    0.47
     informée
    0.46
     گوئی
    0.46
    జర్
    0.46
     રાશિફળ
    0.45
    पश्च
    0.44
     plufieurs
    0.44
     wealthier
    0.44
     thérapeut
    0.43
    жні
    0.43
    Activations Density 0.000%

    No Known Activations