© 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. 40874
    Prev
    Next
    INDEX
    Explanations

    time intervals

    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
     are
    -1.68
    tanleria
    -1.55
    ísticos
    -1.47
     worin
    -1.43
    daw
    -1.38
    ghalaya
    -1.36
    OCTOBER
    -1.35
    😞
    -1.34
    clap
    -1.33
    utrients
    -1.32
    POSITIVE LOGITS
     долла
    1.57
    _
    1.48
     endowed
    1.39
    "
    1.38
    نتیجه
    1.31
     снова
    1.30
    以上です
    1.28
    Since
    1.28
     опять
    1.27
    夕方
    1.26
    Activations Density 0.010%

    No Known Activations