© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38326
    Prev
    Next
    INDEX
    Explanations

    land title and deed sale

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

    The neuron selectively flags passages that enumerate or quantify things—numbers, measurements, lists of items, or formal “if/when/but” clauses presenting specific values or conditions.

    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
    ienka
    -0.82
     stá
    -0.75
     سينما
    -0.75
     ولك
    -0.73
    dci
    -0.72
    ட்ச
    -0.71
     Fingerprint
    -0.69
    owanym
    -0.68
    ruitment
    -0.68
    చ్
    -0.67
    POSITIVE LOGITS
     title
    4.91
    title
    3.94
     Title
    3.69
     titles
    3.55
    Title
    3.55
     TITLE
    3.41
     título
    3.25
    TITLE
    3.03
     Titles
    2.78
     getTitle
    2.78
    Activations Density 0.030%

    No Known Activations