© 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. 6966
    Prev
    Next
    INDEX
    Explanations

    view point of

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

    This neuron fires on the very first substantial content word (typically a noun) at the start of each new text segment.

    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
    s
    -2.33
    }
    -2.23
    te
    -1.83
    ar
    -1.83
    ↵
    -1.67
    ?
    -1.67
    v
    -1.64
    m
    -1.63
    "
    -1.59
    an
    -1.57
    POSITIVE LOGITS
    媄
    1.86
    鹇
    1.77
    鸲
    1.76
     Acuerdo
    1.70
    vió
    1.70
     dengan
    1.68
    zzlies
    1.61
     mirip
    1.59
    følge
    1.59
    МЫ
    1.58
    Activations Density 0.047%

    No Known Activations