© 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. 10-GEMMASCOPE-RES-131K
    7. 128500
    Prev
    Next
    INDEX
    Explanations

    programming code snippets, mixed languages

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

    This neuron detects tokens from Czech/Slovak text (i.e. non-English Slavic words with diacritics).

    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
     know
    -1.25
    泞
    -1.17
    crites
    -1.17
     ваш
    -1.16
     delicado
    -1.13
     of
    -1.13
    ではまた
    -1.13
    graben
    -1.12
    ためには
    -1.11
    ריך
    -1.10
    POSITIVE LOGITS
     toolStrip
    1.47
     essendo
    1.41
    𝗣
    1.32
     diventato
    1.29
    ënten
    1.27
    有时候
    1.24
     facendo
    1.23
     buenas
    1.23
    InSection
    1.20
     andato
    1.18
    Activations Density 0.006%

    No Known Activations