© 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. 22-GEMMASCOPE-RES-131K
    7. 36576
    Prev
    Next
    INDEX
    Explanations

    French words following 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_22/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
     that
    -1.33
     first
    -1.19
     their
    -1.17
     this
    -1.13
     any
    -1.13
     such
    -1.11
     like
    -1.11
    4
    -1.09
     these
    -1.00
    6
    -0.96
    POSITIVE LOGITS
     applau
    1.30
     postale
    1.30
     conster
    1.21
     inaugu
    1.19
     grotte
    1.18
     frontale
    1.17
     raya
    1.16
     granito
    1.15
     ronde
    1.13
     majest
    1.12
    Activations Density 0.002%

    No Known Activations