© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37922
    Prev
    Next
    INDEX
    Explanations

    script comments and conditionals

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imit
    -0.77
     صدا
    -0.67
     Dene
    -0.66
    肄
    -0.66
     semana
    -0.65
    ablecer
    -0.65
    了出来
    -0.65
     benefitted
    -0.64
    лым
    -0.63
    ARL
    -0.63
    POSITIVE LOGITS
    Swiper
    0.74
    Volatile
    0.68
     LLC
    0.67
    ленность
    0.66
     UART
    0.66
    Regions
    0.65
     Ety
    0.65
     pylint
    0.65
     hören
    0.64
    Synth
    0.64
    Activations Density 0.062%

    No Known Activations