© 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. 35863
    Prev
    Next
    INDEX
    Explanations

    sentence starters and 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
     liền
    -0.97
     remb
    -0.95
     ceb
    -0.95
    篳
    -0.94
     poliester
    -0.93
     iemand
    -0.92
    ופת
    -0.91
     genial
    -0.90
     pérd
    -0.90
     Aún
    -0.90
    POSITIVE LOGITS
     and
    1.15
     later
    1.04
    usata
    1.02
     or
    1.02
    ähig
    1.00
     with
    0.96
    vehicle
    0.94
     scrittore
    0.93
    基本的
    0.92
     each
    0.91
    Activations Density 0.000%

    No Known Activations