© 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. 26789
    Prev
    Next
    INDEX
    Explanations

    instead, because, transition

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

    This neuron strongly responds to clause- or sentence-boundary markers—especially semicolons and the pronouns (We, he, I, His) or short linking words that begin new clauses.

    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
     Rumuni
    -0.93
    stande
    -0.86
    likasi
    -0.86
    lántico
    -0.85
     mapStateToProps
    -0.85
    зера
    -0.85
    残念ながら
    -0.84
     hierv
    -0.83
    راحی
    -0.83
    ورية
    -0.82
    POSITIVE LOGITS
     instead
    1.74
     because
    1.73
     Instead
    1.72
    Instead
    1.53
    而是
    1.31
     it
    1.25
    instead
    1.16
     perché
    1.15
     porque
    1.14
     invece
    1.14
    Activations Density 0.022%

    No Known Activations