© 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. 34-GEMMASCOPE-RES-131K
    7. 31532
    Prev
    Next
    INDEX
    Explanations

    adjectives modifying place

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

    The neuron fires on the word “place” when it appears in idiomatic phrases (e.g. “get from one place to another,” “make the world a better place”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    *}[
    -0.82
    tać
    -0.79
    issão
    -0.78
    Uwagi
    -0.77
    点は
    -0.77
    emptions
    -0.75
    他就
    -0.74
    OfBirth
    -0.73
    ➚
    -0.73
    StoryboardSegue
    -0.72
    POSITIVE LOGITS
     place
    7.38
     places
    6.50
    place
    4.91
    Place
    4.66
    places
    4.53
     lugar
    4.41
     Places
    4.28
    Places
    4.28
     Place
    4.19
     lugares
    4.06
    Activations Density 0.192%

    No Known Activations