© 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. 69068
    Prev
    Next
    INDEX
    Explanations

    following:

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

    The neuron flags structural markers in technical text—especially colons that introduce “the following” and numerical list or section labels (e.g. “1.”, “2.”, etc.).

    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
     Empower
    -1.42
     avancer
    -1.41
     ----
    -1.39
     ajan
    -1.38
     lopp
    -1.38
     {
    -1.36
     teki
    -1.35
     gole
    -1.34
    (`${
    -1.34
    -{
    -1.32
    POSITIVE LOGITS
     about
    1.67
     foremost
    1.53
     from
    1.53
     chiefly
    1.52
     regarding
    1.49
     to
    1.47
     including
    1.47
    ですか
    1.43
     despite
    1.43
     =
    1.43
    Activations Density 0.043%

    No Known Activations