© 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. 141403
    Prev
    Next
    INDEX
    Explanations

    narratives, strategies, chain, plant, introduced

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

    simplification and negation

    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
    适应
    0.43
    ਜ
    0.42
     ACTIV
    0.41
     DIRECTOR
    0.40
     ODDS
    0.40
     beneficiaries
    0.40
     BENEFITS
    0.39
    戰
    0.39
    ቋ
    0.38
    mix
    0.38
    POSITIVE LOGITS
     미술
    0.55
     создает
    0.51
    ,»
    0.50
    ?»
    0.49
     tercero
    0.48
     ści
    0.48
     ಲ
    0.48
     testicule
    0.48
     errichtet
    0.48
    вання
    0.47
    Activations Density 0.001%

    No Known Activations