© 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. 41604
    Prev
    Next
    INDEX
    Explanations

    people named Bob

    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
    踅
    -2.55
    谖
    -2.45
    瑧
    -2.33
    剮
    -2.27
     sorprend
    -2.25
    mıştır
    -2.25
     manchmal
    -2.23
     skupiny
    -2.22
    腚
    -2.20
    哢
    -2.17
    POSITIVE LOGITS
    ’
    4.38
    an
    2.70
    的吧
    2.64
    —
    2.53
     wth
    2.53
    刧
    2.47
    ༔
    2.42
    ות
    2.41
    2
    2.39
    The
    2.38
    Activations Density 0.004%

    No Known Activations