© 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. 15133
    Prev
    Next
    INDEX
    Explanations

    of a

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

    The neuron fires most strongly on very common, high‐frequency words (especially function words like “of,” “to,” etc.) rather than rare or specialized terms.

    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
     and
    -2.23
    pergillus
    -2.22
     jahre
    -2.03
    corbic
    -2.02
    sistent
    -1.99
     Diciembre
    -1.95
     Sungai
    -1.95
    juries
    -1.91
     that
    -1.90
    signable
    -1.88
    POSITIVE LOGITS
     a
    7.31
     an
    4.31
     sebuah
    2.89
     একটি
    2.44
    一个
    2.38
     another
    2.33
     one
    2.25
     something
    2.20
     someone
    2.19
     einem
    2.16
    Activations Density 0.672%

    No Known Activations