© 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. 22-GEMMASCOPE-RES-131K
    7. 71057
    Prev
    Next
    INDEX
    Explanations

    Nick Saban, Q: , Anterior cruciate

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

    indentation spacing in code and technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates for numeric tokens (decimal or integer literals, e.g. line numbers or other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    eapples
    -1.04
    {
    -0.99
    isque
    -0.98
    muñ
    -0.98
     mitte
    -0.95
    josé
    -0.95
    ortecedor
    -0.94
     träd
    -0.94
     plafon
    -0.94
    lichte
    -0.94
    POSITIVE LOGITS
    Transkript
    0.89
    ua
    0.83
    It
    0.81
     disad
    0.81
    avelin
    0.81
    lt
    0.80
    _
    0.78
     contingencies
    0.77
     first
    0.77
    一辈子
    0.76
    Activations Density 0.000%

    No Known Activations