© 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. 130226
    Prev
    Next
    INDEX
    Explanations

    numbers followed by 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
    5
    -1.46
    8
    -1.28
     ALSO
    -1.27
    ma
    -1.23
    b
    -1.18
     atualizado
    -1.18
    0
    -1.18
    j
    -1.16
     vermitteln
    -1.13
     aranha
    -1.12
    POSITIVE LOGITS
     It
    1.17
    颪
    1.17
     recenti
    1.16
    seperti
    1.15
    abilirsiniz
    1.08
     viaja
    1.06
     které
    1.05
     amikor
    1.05
     古风
    1.03
     This
    1.02
    Activations Density 0.199%

    No Known Activations