© 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. 111570
    Prev
    Next
    INDEX
    Explanations

    Western Reserve

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

    The neuron primarily detects numeric tokens (numbers and numerical measurements).

    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
     to
    -1.71
    >
    -1.59
     учитывать
    -1.54
     being
    -1.48
    である
    -1.45
     it
    -1.44
     “
    -1.35
     aegis
    -1.35
    ",
    -1.32
     —
    -1.32
    POSITIVE LOGITS
    Mereka
    1.60
    文的
    1.48
     sportivo
    1.47
    Probably
    1.45
    Kemudian
    1.45
    Ꮗ
    1.43
     animato
    1.41
    Sebelumnya
    1.41
    饷
    1.41
    Sedangkan
    1.40
    Activations Density 0.047%

    No Known Activations