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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127284
    Prev
    Next
    INDEX
    Explanations

    foreign language suffixes

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

    This neuron responds to unusually uncommon or low‐frequency tokens, flagging words that stand out as rare or distinctive.

    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
     and
    -4.06
     or
    -1.92
     but
    -1.69
     is
    -1.66
     should
    -1.60
     will
    -1.48
     Should
    -1.41
    ではまた
    -1.34
     When
    -1.34
     "
    -1.31
    POSITIVE LOGITS
     違い
    1.79
     Fotografía
    1.70
    স
    1.66
     juſ
    1.64
     ſmall
    1.63
    нология
    1.63
     ſont
    1.59
    oría
    1.59
     outono
    1.59
     consentimento
    1.57
    Activations Density 0.090%

    No Known Activations