© 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. 60487
    Prev
    Next
    INDEX
    Explanations

    name suffixes

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

    The neuron responds to words that include non‐ASCII Latin characters (letters 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
    It
    -2.23
    ).
    -2.16
    三大
    -2.08
    しましたが
    -2.06
     marvel
    -2.03
     what
    -2.03
    二百
    -1.98
     lebih
    -1.96
    .(
    -1.96
     *
    -1.95
    POSITIVE LOGITS
    鬭
    3.08
     グリル
    2.88
    衚
    2.86
    厛
    2.59
    ’,
    2.53
    뿅
    2.52
    觧
    2.45
    乆
    2.44
    𞤢
    2.42
     フラワー
    2.38
    Activations Density 0.011%

    No Known Activations