© 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. 34-GEMMASCOPE-RES-131K
    7. 80953
    Prev
    Next
    INDEX
    Explanations

    words starting with 'o' or 'b'

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

    The neuron activates on five-letter subsequences of alternating vowel-consonant (v-c-v-c-v) patterns (e.g. ORODO in Horodok, OKOLO in Sokoloff, OMOYO in Tomoyo).

    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
     günlük
    -0.89
     apresentam
    -0.79
    するか
    -0.74
     incluem
    -0.72
    idão
    -0.69
     œufs
    -0.68
    stück
    -0.67
    patient
    -0.66
    cocina
    -0.66
    isque
    -0.66
    POSITIVE LOGITS
    感觉
    0.84
     sexo
    0.79
    ابعة
    0.78
    ߲
    0.77
    ImageLoader
    0.73
    畑
    0.71
    増
    0.70
    мә
    0.69
     Helfer
    0.69
    нику
    0.69
    Activations Density 0.075%

    No Known Activations