© 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. 80952
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

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

    The neuron is highly responsive to numeric tokens—i.e. standalone numbers or digit sequences.

    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
     навіть
    -0.81
    ॢ
    -0.77
     dramatist
    -0.75
    Equations
    -0.73
     mostrarán
    -0.72
    扁平
    -0.72
    一首
    -0.71
     NLA
    -0.71
     jefes
    -0.71
     prefixed
    -0.70
    POSITIVE LOGITS
    gespräch
    0.85
    effect
    0.85
     House
    0.85
    indi
    0.84
    ingu
    0.84
    ique
    0.84
    iscus
    0.84
    IQUE
    0.83
     annually
    0.82
     FY
    0.82
    Activations Density 0.006%

    No Known Activations