© 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. 34-GEMMASCOPE-RES-131K
    7. 56824
    Prev
    Next
    INDEX
    Explanations

    introduction Q A before download

    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
    Negative Logits
    descargar
    -0.85
     クリック
    -0.81
     большин
    -0.78
     negozio
    -0.77
     septem
    -0.75
    CLE
    -0.74
    animales
    -0.72
    isInitialized
    -0.72
     multe
    -0.72
    保育
    -0.70
    POSITIVE LOGITS
    nag
    0.86
    ÈME
    0.79
    кр
    0.77
     zpra
    0.77
     ausgeführt
    0.76
    нении
    0.75
    zeum
    0.75
    廊
    0.74
    nach
    0.74
    没了
    0.74
    Activations Density 0.036%

    No Known Activations