© 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. 58569
    Prev
    Next
    INDEX
    Explanations

    part of

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

    The neuron fires on the word “part” when used to mark a component (e.g. “part of”) 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
    ൎ
    -1.80
    blins
    -1.79
     Such
    -1.77
    山頂
    -1.73
     aprobó
    -1.70
    ;
    -1.70
    xvii
    -1.68
    lepaskan
    -1.66
     wiederholt
    -1.65
     Specially
    -1.65
    POSITIVE LOGITS
     of
    3.28
    le
    2.20
    or
    2.13
    p
    1.91
    d
    1.80
    v
    1.80
    this
    1.78
    mu
    1.74
     vea
    1.71
    j
    1.71
    Activations Density 0.012%

    No Known Activations