© 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. 10-GEMMASCOPE-RES-131K
    7. 48473
    Prev
    Next
    INDEX
    Explanations

    KL variations

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

    The neuron detects tokens that consist of the letters “KL” immediately followed by digits, i.e. “KL”-prefixed codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </i>
    -2.72
    <i>
    -2.41
    <bos>
    -2.36
     aquella
    -2.31
    我一直
    -2.25
    蹀
    -2.19
    起身
    -2.17
     представителей
    -2.16
     人間
    -2.16
    _{
    -2.14
    POSITIVE LOGITS
    ﮨ
    2.56
    (
    2.50
     stratég
    2.50
    𓐍
    2.42
    _
    2.41
     vulgaires
    2.23
     delitos
    2.22
    𓆜
    2.20
     étrang
    2.17
    生死
    2.17
    Activations Density 0.004%

    No Known Activations