© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 82900
    Prev
    Next
    INDEX
    Explanations

    understanding how

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

    Possessiveness, ballbusting, technical contexts

    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
    ルダー
    0.51
    resultados
    0.47
    đa
    0.45
    льних
    0.44
    ठबंधन
    0.44
    ся
    0.43
     exhaustive
    0.42
    τρ
    0.42
    фектив
    0.41
    ռ
    0.41
    POSITIVE LOGITS
     iw
    0.51
     oli
    0.49
    อาหาร
    0.48
     איי
    0.48
     twinning
    0.47
     sustainably
    0.47
     线
    0.46
    สามารถ
    0.46
     পারে
    0.46
     stort
    0.46
    Activations Density 0.000%

    No Known Activations