© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66741
    Prev
    Next
    INDEX
    Explanations

    exist or existence

    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
    signia
    -1.49
    🙇
    -1.39
    利的
    -1.38
     endforeach
    -1.38
    erráneo
    -1.34
    uré
    -1.33
    llten
    -1.32
     oro
    -1.32
    ｙ
    -1.30
    welle
    -1.29
    POSITIVE LOGITS
     nachher
    1.55
     plenamente
    1.41
    つは
    1.40
    corpion
    1.34
     Thirty
    1.33
     are
    1.31
     permitan
    1.31
     její
    1.29
     today
    1.27
    dreamstime
    1.27
    Activations Density 0.168%

    No Known Activations