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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32685
    Prev
    Next
    INDEX
    Explanations

    early life section

    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
     две
    -0.71
    agre
    -0.67
     economia
    -0.66
    ouders
    -0.65
    亚
    -0.64
    gı
    -0.63
     cintura
    -0.62
    ティア
    -0.62
    выя
    -0.61
    fchen
    -0.61
    POSITIVE LOGITS
     میر
    0.76
    vcpu
    0.69
    unga
    0.65
     Zhan
    0.65
    eker
    0.63
     Clarkson
    0.63
    駿
    0.61
     અને
    0.61
     inadvert
    0.59
    ButtonModule
    0.59
    Activations Density 0.118%

    No Known Activations