© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23747
    Prev
    Next
    INDEX
    Explanations

    factorial, sum, average, square

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,-\
    0.39
    εκ
    0.39
    ኺ
    0.38
     Ком
    0.38
     Cache
    0.37
    DUCED
    0.37
     Contemporary
    0.36
    Versioning
    0.36
     preserving
    0.36
     AL
    0.36
    POSITIVE LOGITS
     fichiers
    0.36
     soluções
    0.35
    लेले
    0.34
     puno
    0.34
    싶
    0.34
     factorial
    0.34
    coats
    0.34
     solicitado
    0.33
     stuffed
    0.33
     싶
    0.33
    Activations Density 0.001%

    No Known Activations