© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72565
    Prev
    Next
    INDEX
    Explanations

    but especially it have

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

    The neuron strongly activates on comma punctuation (with a smaller secondary response to the word “but”).

    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
     and
    -2.22
    </h2>
    -1.53
    .”
    -1.45
    ></
    -1.41
    ↵↵
    -1.33
    .}
    -1.28
     etc
    -1.28
    ).
    -1.25
    </h1>
    -1.23
    </h5>
    -1.13
    POSITIVE LOGITS
     creemos
    1.27
    中略
    1.26
    馊
    1.22
     However
    1.19
    イイ
    1.16
    カワ
    1.14
     azonban
    1.13
    論
    1.13
    किन
    1.12
    も多く
    1.11
    Activations Density 0.059%

    No Known Activations