© 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. 3776
    Prev
    Next
    INDEX
    Explanations

    text segments starting with specific entities or punctuation

    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
    B
    -1.73
    d
    -1.61
    _
    -1.48
     ehe
    -1.47
    up
    -1.45
     until
    -1.44
     sguardo
    -1.39
    н
    -1.38
    ta
    -1.38
     From
    -1.36
    POSITIVE LOGITS
    bilir
    1.60
     größere
    1.42
     ‘‘
    1.39
     dritte
    1.36
     grüne
    1.35
    ーーーー
    1.34
     schönsten
    1.34
     Malawi
    1.32
    台風
    1.31
     Hinblick
    1.31
    Activations Density 0.010%

    No Known Activations