© 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. 124099
    Prev
    Next
    INDEX
    Explanations

    programming attributes and classes

    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
    、
    -1.55
     accompagner
    -1.55
     cuisson
    -1.46
     нѣ
    -1.43
    öffnung
    -1.41
    馊
    -1.41
    Hlav
    -1.39
    bewegung
    -1.38
     ごはん
    -1.38
     вѣ
    -1.35
    POSITIVE LOGITS
     –
    1.90
     will
    1.82
     is
    1.80
     There
    1.58
     but
    1.57
     Although
    1.48
     This
    1.44
     -
    1.42
     It
    1.41
    there
    1.40
    Activations Density 0.012%

    No Known Activations