© 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. 93911
    Prev
    Next
    INDEX
    Explanations

    CSR and certificates

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

    The neuron fires on numeric literals—especially standalone numbers (like key‐sizes or other numeric parameters).

    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
    DTD
    -0.75
    {_
    -0.73
    élection
    -0.73
    -<
    -0.72
    ISTRY
    -0.72
     UPDATED
    -0.71
    óp
    -0.70
    <mask>
    -0.69
     område
    -0.68
    exclusive
    -0.66
    POSITIVE LOGITS
    CSR
    1.54
     CSR
    1.54
    csr
    1.38
    Thumb
    1.15
     thumb
    1.13
     Thumb
    1.08
    thumb
    1.05
     cs
    0.90
     getRequest
    0.79
    enrollment
    0.77
    Activations Density 0.084%

    No Known Activations