© 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. 48414
    Prev
    Next
    INDEX
    Explanations

    specific nouns or descriptions

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

    The neuron never activates on any tokens—it isn’t detecting any pattern.

    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
    ကိုးကား
    -1.45
     this
    -1.44
     like
    -1.44
    鹩
    -1.41
     thereafter
    -1.39
     लेकिन
    -1.38
    の高い
    -1.37
     LIRE
    -1.36
    也会
    -1.35
     çocuklar
    -1.34
    POSITIVE LOGITS
    usive
    1.79
    .
    1.70
    uride
    1.68
     and
    1.66
    oys
    1.64
    usions
    1.63
    yled
    1.62
    iric
    1.51
    lllllll
    1.50
    antism
    1.50
    Activations Density 0.088%

    No Known Activations