© 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. 34-GEMMASCOPE-RES-131K
    7. 49189
    Prev
    Next
    INDEX
    Explanations

    whether something is

    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
     não
    -1.85
    ไม่
    -1.83
     δεν
    -1.80
     không
    -1.79
     neither
    -1.71
     rất
    -1.68
     tidak
    -1.67
    ไม่ได้
    -1.66
    probably
    -1.60
    cannot
    -1.55
    POSITIVE LOGITS
     any
    2.42
     or
    2.36
     ever
    2.09
     really
    1.90
     actually
    1.89
     truly
    1.84
     still
    1.80
     even
    1.73
    有任何
    1.71
     wirklich
    1.66
    Activations Density 0.169%

    No Known Activations