© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64255
    Prev
    Next
    INDEX
    Explanations

    android activity onCreate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     mariposa
    -1.24
     instala
    -1.12
     puto
    -1.10
     piment
    -1.10
    ܊
    -1.09
     bombas
    -1.08
     churras
    -1.08
     Bajos
    -1.05
     bolos
    -1.05
     zapatillas
    -1.05
    POSITIVE LOGITS
    значение
    1.00
    QUENCE
    0.93
     from
    0.92
    ongeza
    0.92
    PDE
    0.91
     artisanal
    0.89
     mewujudkan
    0.89
     esencia
    0.88
    diator
    0.88
    オプション
    0.85
    Activations Density 0.001%

    No Known Activations