© 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. 10-GEMMASCOPE-RES-131K
    7. 85604
    Prev
    Next
    INDEX
    Explanations

    specific topic starters

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

    This neuron fires on the “]:” sequence that marks section or metadata labels (e.g. “Source:]”, “Chorus:]”, “Photo Gallery:]”).

    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
    $
    -1.82
    飭
    -1.76
     barbati
    -1.68
    A
    -1.66
    褫
    -1.54
     时尚
    -1.52
     ilumina
    -1.52
    迓
    -1.51
     WHAT
    -1.49
     disponer
    -1.49
    POSITIVE LOGITS
    </b>
    1.93
    1.65
    女孩子
    1.65
     â
    1.52
     «
    1.52
    こない
    1.48
     ``
    1.46
    メージ
    1.45
     Может
    1.42
    肮
    1.41
    Activations Density 0.000%

    No Known Activations