© 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. 65900
    Prev
    Next
    INDEX
    Explanations

    question and answer formats

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

    The neuron strongly activates on the literal “\r” escape sequence, i.e. carriage‐return line‐break markers.

    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
    は
    -2.39
    などの
    -2.14
    ！』
    -1.98
     kehilangan
    -1.96
    ・・・」
    -1.95
     by
    -1.92
     in
    -1.86
     all
    -1.85
    子は
    -1.85
     numerous
    -1.81
    POSITIVE LOGITS
    B
    2.44
    addCriterion
    2.16
     cómodo
    2.08
    @[+][
    1.90
    為に
    1.88
     atractivo
    1.81
     créer
    1.80
     participer
    1.79
    yarnpkg
    1.73
     curtailed
    1.73
    Activations Density 0.000%

    No Known Activations