© 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. 72956
    Prev
    Next
    INDEX
    Explanations

    discusses or shares information

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

    The neuron is simply tracking each token’s position in the text, with activation rising roughly in proportion to its index.

    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
     in
    -1.66
     if
    -1.49
     by
    -1.43
     for
    -1.32
     at
    -1.32
     after
    -1.30
     this
    -1.16
     add
    -1.16
     because
    -1.14
    Now
    -1.14
    POSITIVE LOGITS
     his
    1.73
     ſeveral
    1.63
     interesantes
    1.38
     about
    1.36
    ཊ
    1.34
     molte
    1.34
     dát
    1.32
     miniaturka
    1.30
     praticamente
    1.29
     ním
    1.29
    Activations Density 0.030%

    No Known Activations