© 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. 942
    Prev
    Next
    INDEX
    Explanations

    names and places starting with "Vo"

    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
    which
    -3.34
    鬟
    -3.28
    仃
    -2.64
    䉴
    -2.58
    屃
    -2.56
    寕
    -2.48
    ⬯
    -2.47
    嵛
    -2.45
     pressured
    -2.44
    geſ
    -2.42
    POSITIVE LOGITS
    _
    3.45
    *
    3.08
    --
    3.00
    e
    2.89
    9
    2.88
    2
    2.77
    a
    2.59
    es
    2.59
     homage
    2.53
     It
    2.52
    Activations Density 0.002%

    No Known Activations