© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63985
    Prev
    Next
    INDEX
    Explanations

    German word beginnings and endings

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

    The neuron activates on tokens containing non-ASCII letters—especially Germanic characters with diacritics (e.g. umlauts or accented forms).

    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
     Keene
    -0.75
    vast
    -0.73
    --*/
    -0.72
    ආ
    -0.71
    ž
    -0.70
    ramientas
    -0.69
    oform
    -0.69
    faction
    -0.69
    iodía
    -0.69
    jada
    -0.69
    POSITIVE LOGITS
    Overlap
    0.77
    tigung
    0.75
     ダイヤモンド
    0.75
     fraudul
    0.72
     proper
    0.71
    Maximize
    0.71
    chen
    0.71
    ליך
    0.69
    lein
    0.68
     Ngb
    0.68
    Activations Density 0.015%

    No Known Activations