© 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. 58324
    Prev
    Next
    INDEX
    Explanations

    ghost productions

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

    The main thing this neuron does is detect occurrences of the word “ghost” (and its close morphological variants).

    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
    of
    -3.06
    跸
    -2.83
     algum
    -2.80
    蕺
    -2.66
    氿
    -2.44
    就算是
    -2.39
    茈
    -2.36
    ⩴
    -2.36
     ofrecerte
    -2.34
    躥
    -2.34
    POSITIVE LOGITS
    }
    2.95
     of
    2.56
    และ
    2.16
    Затем
    2.14
     ומ
    2.09
    돛
    2.09
    而
    2.06
    ၞ
    2.02
    Далее
    1.98
    通貨
    1.98
    Activations Density 0.007%

    No Known Activations