© 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. 73196
    Prev
    Next
    INDEX
    Explanations

    reduce, enable, expand, increase

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

    The neuron selectively lights up on content‐bearing words—especially scientific or technical verbs and key nouns (e.g. “reducing,” “increasing,” “deliver,” “levels”) that convey quantitative or mechanistic actions.

    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
     it
    -1.48
     also
    -1.23
     any
    -1.16
     as
    -1.16
     with
    -1.13
     three
    -1.12
    店長
    -1.11
     at
    -1.09
     some
    -1.08
     rudimentary
    -1.06
    POSITIVE LOGITS
     maniere
    1.22
     degrés
    1.22
     bensin
    1.19
     délais
    1.16
     teater
    1.13
    盍
    1.13
    onete
    1.12
     ausreichend
    1.09
     italiens
    1.09
     frete
    1.07
    Activations Density 0.109%

    No Known Activations