© 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. 1369
    Prev
    Next
    INDEX
    Explanations

    keywords followed by punctuation or specific 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
     ‚
    -1.89
     amd
    -1.72
     ï
    -1.70
     of
    -1.70
    颪
    -1.66
     nhưng
    -1.64
    ﮦ
    -1.61
     anſ
    -1.59
     และ
    -1.55
    轵
    -1.55
    POSITIVE LOGITS
     it
    1.99
     there
    1.84
     any
    1.59
     this
    1.52
     like
    1.49
     also
    1.48
     tries
    1.43
    (
    1.41
     similar
    1.40
     had
    1.38
    Activations Density 0.055%

    No Known Activations