© 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. 10-GEMMASCOPE-RES-131K
    4. 105055
    Prev
    Next
    INDEX
    Explanations

    heuristic methods and models

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

    the word "heuristic" or "heuristics" in academic and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the term “heuristic,” i.e. references to heuristic methods or approaches.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     или
    -2.52
    坶
    -2.39
    ꜆
    -2.39
     annoncé
    -2.34
    voyez
    -2.31
    ciendo
    -2.30
    禔
    -2.20
     extérieur
    -2.20
    恹
    -2.19
    zenie
    -2.16
    POSITIVE LOGITS
    0
    2.77
    );
    2.34
    B
    2.25
    .
    2.23
    F
    2.22
     if
    2.14
    {
    2.08
    と話
    1.99
     Preguntas
    1.98
    なのだ
    1.91
    Activations Density 0.002%

    No Known Activations