© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104363
    Prev
    Next
    INDEX
    Explanations

    Hurricane Earl

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

    The neuron doesn’t detect any particular token pattern—it remains inactive on all input.

    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
    _
    -2.53
    $
    -2.05
    *
    -2.03
    [
    -1.93
    \
    -1.82
    For
    -1.66
    n
    -1.65
    <
    -1.65
     sebagainya
    -1.59
    f
    -1.59
    POSITIVE LOGITS
     jejich
    1.66
     a
    1.62
    canakan
    1.59
     προϊόν
    1.59
     Süden
    1.58
     this
    1.57
    ablecer
    1.55
    唛
    1.55
    tahu
    1.52
     museos
    1.51
    Activations Density 0.000%

    No Known Activations