© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72278
    Prev
    Next
    INDEX
    Explanations

    Volcano, underwear, telescope

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

    The neuron strongly responds to longer, multi‐syllable content words (especially specialized nouns).

    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
    ed
    -3.50
    al
    -2.97
    la
    -2.92
    ri
    -2.89
    ly
    -2.88
    ro
    -2.86
    ie
    -2.70
    潆
    -2.61
    鹩
    -2.52
    nd
    -2.50
    POSITIVE LOGITS
    .
    3.00
    逦
    2.59
     เพราะ
    2.44
    因为他
    2.42
    櫚
    2.42
    喽
    2.39
     salvación
    2.22
     یک
    2.19
     Universidades
    2.17
    虜
    2.14
    Activations Density 0.007%

    No Known Activations