© 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. 69783
    Prev
    Next
    INDEX
    Explanations

    agree that

    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
     other
    -1.80
     kabupaten
    -1.64
     harapan
    -1.56
     interestingly
    -1.49
    nologue
    -1.48
     of
    -1.48
     for
    -1.47
     mimpi
    -1.46
     भी
    -1.45
     catatan
    -1.45
    POSITIVE LOGITS
    0
    1.77
    あー
    1.63
    "
    1.51
    还是很
    1.39
    entreprise
    1.38
     GABA
    1.38
    1
    1.34
     gesprek
    1.33
    waarde
    1.32
     capitaine
    1.31
    Activations Density 0.007%

    No Known Activations