© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77149
    Prev
    Next
    INDEX
    Explanations

    Jah, Jh, Joh, Henry

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

    This neuron detects the character sequence “jh” in words (e.g. names like Jhan or Jah).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ccedil
    -0.77
    ']):
    -0.75
    ">)</
    -0.75
    役
    -0.73
    𝑘
    -0.71
     Aleks
    -0.71
    aquin
    -0.71
    hman
    -0.70
     statistic
    -0.69
    君子
    -0.69
    POSITIVE LOGITS
     Swansea
    0.73
    responseType
    0.73
    Coupon
    0.73
    verze
    0.72
     الرسمي
    0.72
     Jh
    0.71
    𝟲
    0.71
    TERA
    0.71
    ᆹ
    0.70
     JOH
    0.69
    Activations Density 0.014%

    No Known Activations