© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64965
    Prev
    Next
    INDEX
    Explanations

    copyright notices and code headers

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

    The neuron strongly activates on long runs of whitespace characters (e.g. repeated spaces or tabs).

    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
    Both
    -1.11
    Penjelasan
    -1.09
    when
    -1.09
     When
    -1.01
    Every
    -1.00
    𝙣
    -0.98
     Each
    -0.96
    他にも
    -0.96
    providedIn
    -0.96
     both
    -0.96
    POSITIVE LOGITS
     ck
    1.04
    w
    1.00
     Dinas
    0.98
     espesor
    0.98
    搅拌
    0.98
    presso
    0.92
    打开了
    0.91
     keny
    0.91
     lc
    0.91
    かります
    0.91
    Activations Density 0.023%

    No Known Activations