© 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. 68164
    Prev
    Next
    INDEX
    Explanations

    of course

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

    The neuron fires on the preposition “of.”

    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
     the
    -2.67
    他说
    -2.41
    the
    -2.38
    ÁRIO
    -2.30
     regi
    -2.25
    說道
    -2.20
    說
    -2.19
    先日
    -2.14
    from
    -2.13
    梣
    -2.11
    POSITIVE LOGITS
     The
    2.84
     It
    2.66
    溏
    2.42
     This
    2.39
     Тип
    2.36
    饧
    2.34
     entrar
    2.28
     They
    2.25
    大多
    2.22
     niemand
    2.19
    Activations Density 0.096%

    No Known Activations