© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93307
    Prev
    Next
    INDEX
    Explanations

    construction, sequence, connection

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

    The neuron is triggered by Cyrillic letter sequences (i.e. Russian word substrings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ࿙
    -1.71
    motorola
    -1.63
     from
    -1.58
     by
    -1.51
    ﾛ
    -1.46
     kering
    -1.45
     of
    -1.45
    ﾜ
    -1.44
    larınız
    -1.43
    Lá
    -1.40
    POSITIVE LOGITS
    ang
    1.85
    ou
    1.65
    eng
    1.62
    ⚣
    1.60
    ar
    1.60
    U
    1.59
    in
    1.56
    ut
    1.55
    C
    1.55
    T
    1.52
    Activations Density 0.043%

    No Known Activations