© 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. 93239
    Prev
    Next
    INDEX
    Explanations

    closing quote or punctuation followed by text

    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
     aturan
    -1.06
    甶
    -1.03
     zowel
    -1.00
     صفح
    -0.98
    在美国
    -0.97
     elenco
    -0.97
    actually
    -0.96
    abetes
    -0.95
     chiamato
    -0.94
     تعد
    -0.93
    POSITIVE LOGITS
     according
    2.22
     según
    1.38
    According
    1.30
     (
    1.28
     selon
    1.23
    according
    1.14
     According
    1.13
     described
    1.12
     согласно
    1.07
     enligt
    1.05
    Activations Density 0.026%

    No Known Activations