© 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. 10-GEMMASCOPE-RES-131K
    7. 110745
    Prev
    Next
    INDEX
    Explanations

    usual situation

    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
     fünf
    -2.75
    臜
    -2.70
     onze
    -2.69
    了出来
    -2.53
    跸
    -2.52
     vijf
    -2.47
    瘊
    -2.45
     COULD
    -2.44
    阄
    -2.44
     wondrous
    -2.42
    POSITIVE LOGITS
    a
    3.58
    s
    3.25
    l
    3.20
    p
    2.92
    er
    2.80
    ad
    2.64
    r
    2.63
    la
    2.41
    richlet
    2.39
    le
    2.38
    Activations Density 0.004%

    No Known Activations