© 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. 64927
    Prev
    Next
    INDEX
    Explanations

    project-version

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

    The neuron is detecting newline characters (line breaks).

    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
    
    -2.88
    ⩩
    -2.44
    ⮜
    -2.41
     selanjutnya
    -2.34
    鴣
    -2.28
     oleh
    -2.20
    旯
    -2.16
    vège
    -2.14
     lainnya
    -2.14
     which
    -2.13
    POSITIVE LOGITS
    "
    2.61
    \
    2.58
     '
    2.47
    +
    2.38
    We
    2.36
    AL
    2.23
    /
    2.17
    [
    2.16
    '
    2.14
     grueso
    2.11
    Activations Density 0.004%

    No Known Activations