© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57372
    Prev
    Next
    INDEX
    Explanations

    foreign characters and words

    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
     it
    -2.13
     if
    -2.06
     some
    -2.05
     an
    -2.02
     the
    -2.02
    肅
    -1.94
     another
    -1.87
    -
    -1.87
     one
    -1.85
     first
    -1.66
    POSITIVE LOGITS
     –
    2.06
    依然
    1.93
     olika
    1.92
     africana
    1.88
     capitulo
    1.82
    特に
    1.80
    ’
    1.80
     cubana
    1.79
     voidaan
    1.75
    (!__
    1.75
    Activations Density 0.054%

    No Known Activations