© 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. 86286
    Prev
    Next
    INDEX
    Explanations

    directing to a resource

    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
     Terkait
    -2.08
     Sekarang
    -1.84
     Selanjutnya
    -1.72
     Since
    -1.72
     you
    -1.70
     Hingga
    -1.70
    比べて
    -1.69
     Beberapa
    -1.69
     Sebagai
    -1.63
     Meskipun
    -1.62
    POSITIVE LOGITS
     trám
    1.91
    ଃ
    1.80
    鲧
    1.74
    髕
    1.73
     italianos
    1.69
    뮐
    1.69
     griego
    1.66
    。
    1.61
     joka
    1.59
     التواصل
    1.59
    Activations Density 0.019%

    No Known Activations