© 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. 22-GEMMASCOPE-RES-131K
    7. 15151
    Prev
    Next
    INDEX
    Explanations

    in part due to

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

    The neuron is strongly triggered by the word “part” (e.g. in “in part”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Either
    -1.28
    要么
    -1.27
     either
    -1.22
    ither
    -1.20
     laquelle
    -1.13
    거나
    -1.12
    ONLY
    -1.11
     pertes
    -1.09
     komen
    -1.09
     meub
    -1.09
    POSITIVE LOGITS
     because
    1.80
     also
    1.57
     by
    1.46
     due
    1.29
     but
    1.23
     through
    1.21
     some
    1.18
     partially
    1.16
     even
    1.16
     partly
    1.13
    Activations Density 0.029%

    No Known Activations