© 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. 10-GEMMASCOPE-RES-131K
    7. 69843
    Prev
    Next
    INDEX
    Explanations

    foreign or placeholder words

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

    This neuron fires on the very first content word of each new utterance or sentence (i.e. the leading token at the start of a line or message).

    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
     but
    -1.84
    launched
    -1.55
     makam
    -1.55
     marah
    -1.49
     miliki
    -1.48
     langit
    -1.47
     tulis
    -1.46
     matang
    -1.45
    idać
    -1.44
    ཫ
    -1.44
    POSITIVE LOGITS
     prépare
    1.55
    ଶ
    1.53
    ṝ
    1.45
     dilaksanakan
    1.39
     voulais
    1.36
     görmek
    1.36
     desapar
    1.34
     bahç
    1.33
     adatto
    1.31
    ଵ
    1.31
    Activations Density 0.078%

    No Known Activations