© 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. 10-GEMMASCOPE-RES-131K
    7. 43725
    Prev
    Next
    INDEX
    Explanations

    labels and headings

    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_10/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
    m
    -1.76
    k
    -1.73
    s
    -1.62
    f
    -1.56
     those
    -1.45
    ge
    -1.32
     it
    -1.31
    },
    -1.25
    kében
    -1.25
    r
    -1.24
    POSITIVE LOGITS
     instead
    1.48
    wendi
    1.38
    instead
    1.38
    AMIENTO
    1.36
     Saúde
    1.35
     zei
    1.35
    呦
    1.34
    ÁN
    1.30
     Dokter
    1.29
    なく
    1.28
    Activations Density 0.015%

    No Known Activations