© 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. 128523
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on content-bearing words—nouns, verbs, and adjectives—rather than on function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    positive adjectives and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -1.09
     with
    -1.02
    paž
    -0.91
     Полу
    -0.91
     about
    -0.91
     ബ
    -0.88
     known
    -0.87
     and
    -0.86
    前後
    -0.85
    bermuda
    -0.84
    POSITIVE LOGITS
    ografia
    1.12
    ilidades
    1.10
    ⊳
    1.08
     חיצוני
    1.07
    ytä
    1.06
    gunas
    1.03
     ramo
    1.02
     nonostante
    1.02
     کرد
    1.01
    ﺋ
    1.01
    Activations Density 0.022%

    No Known Activations