© 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. 64873
    Prev
    Next
    INDEX
    Explanations

    direction and movement

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

    This neuron fires on content words in technical or scientific explanations, i.e. terms found in math/physics-style descriptions.

    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
     бампер
    -1.68
    ︲
    -1.38
    ocirc
    -1.36
     extremely
    -1.35
     significantly
    -1.31
     incredibly
    -1.31
     utilisé
    -1.29
     publier
    -1.28
    ִּ
    -1.27
    brities
    -1.25
    POSITIVE LOGITS
     at
    1.77
    ֩
    1.28
    "$
    1.27
    ׇ
    1.26
    styrelsen
    1.23
     there
    1.22
    餚
    1.21
     thinks
    1.21
     $\
    1.20
    ,"\
    1.20
    Activations Density 0.017%

    No Known Activations