© 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. 34-GEMMASCOPE-RES-131K
    7. 99829
    Prev
    Next
    INDEX
    Explanations

    various scripts and languages

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

    This neuron detects tokens written in non-Latin scripts (e.g. Devanagari, Bengali, Arabic, Thai, Tibetan characters).

    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
    ce
    -0.81
    蠟
    -0.78
    谆
    -0.74
    normalization
    -0.73
     Absent
    -0.73
    kou
    -0.73
    avadoc
    -0.72
     muun
    -0.71
     comment
    -0.71
     marron
    -0.71
    POSITIVE LOGITS
     permett
    0.96
    ният
    0.88
    ຣ
    0.86
    すっ
    0.82
     acaba
    0.82
     relaciones
    0.81
     cír
    0.81
     experiencias
    0.80
    の方に
    0.80
     мать
    0.79
    Activations Density 0.005%

    No Known Activations