© 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. 54104
    Prev
    Next
    INDEX
    Explanations

    entity names and titles

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

    This neuron is keyed to numeric literals (sequences of digits) in code or text.

    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
     Berry
    -0.76
    Matching
    -0.75
     ber
    -0.74
     blocks
    -0.74
     Cap
    -0.72
    ーンズ
    -0.71
     Sar
    -0.69
    operation
    -0.68
     Sel
    -0.68
    pes
    -0.68
    POSITIVE LOGITS
     entity
    1.03
     projectile
    0.88
     entities
    0.88
     parlement
    0.79
     шоу
    0.78
     throw
    0.77
     riding
    0.76
     ſou
    0.76
    coeffs
    0.76
     manuten
    0.76
    Activations Density 0.004%

    No Known Activations