© 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. 128678
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the token “LINE,” i.e. markers of article bylines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Q: or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    providedIn
    -1.34
    になるので
    -1.34
    為に
    -1.34
    をご覧
    -1.27
    に入れる
    -1.26
    ようです
    -1.25
    で見る
    -1.25
    を行いました
    -1.23
    corrhi
    -1.23
    或者是
    -1.20
    POSITIVE LOGITS
     by
    2.39
     with
    1.79
    は
    1.75
     his
    1.63
     of
    1.63
    で
    1.59
     are
    1.55
    岁的
    1.50
    ……。
    1.50
    には
    1.37
    Activations Density 0.000%

    No Known Activations