© 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. 102563
    Prev
    Next
    INDEX
    Explanations

    location or placement

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

    The neuron is keyed to the markers of step‐by‐step instructions—bullet dashes, run‐and‐make commands, directory names, section headings, etc.—i.e. list items in technical “how‐to” or build/docs instructions.

    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
     besonders
    -0.91
     erbjuder
    -0.89
     through
    -0.85
     виправивши
    -0.85
     через
    -0.84
    了一些
    -0.84
    "]();
    -0.83
    احبه
    -0.82
     ruas
    -0.82
    ⇄
    -0.81
    POSITIVE LOGITS
     located
    2.11
    located
    1.85
     under
    1.55
    Located
    1.45
     ubicada
    1.41
    under
    1.30
     inside
    1.29
     placed
    1.23
     berada
    1.22
    placed
    1.21
    Activations Density 0.260%

    No Known Activations