© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128656
    Prev
    Next
    INDEX
    Explanations

    binomial coefficients

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on non-printable or unusual control/byte characters embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     unrelenting
    -2.77
     undeniably
    -2.69
     burgeoning
    -2.66
     Usually
    -2.64
     strives
    -2.53
     for
    -2.53
     When
    -2.48
     exquisitely
    -2.47
     ALWAYS
    -2.47
    After
    -2.47
    POSITIVE LOGITS
    蠖
    2.78
     famoso
    2.55
    睃
    2.44
    蹰
    2.39
     decidedly
    2.36
     soooo
    2.31
     delightfully
    2.31
     astounding
    2.31
     revamped
    2.30
     sooo
    2.28
    Activations Density 0.014%

    No Known Activations