© 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. 34-GEMMASCOPE-RES-131K
    7. 75709
    Prev
    Next
    INDEX
    Explanations

    and/& followed by capitalized nouns

    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_34/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
     αὐτ
    -0.77
    ĝo
    -0.77
     Chí
    -0.73
    össe
    -0.71
     badan
    -0.71
    頃は
    -0.69
    epiece
    -0.69
     iga
    -0.68
     স
    -0.67
    Síguenos
    -0.66
    POSITIVE LOGITS
     Tuesday
    1.72
     Tuesdays
    1.66
     tales
    1.57
     trib
    1.52
     trava
    1.47
     tale
    1.45
     tresses
    1.41
     tuesday
    1.41
     troubles
    1.40
     ট
    1.39
    Activations Density 0.105%

    No Known Activations