© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86048
    Prev
    Next
    INDEX
    Explanations

    code directives

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

    The neuron activates on the “@” character.

    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
     about
    -1.88
     {\
    -1.61
     tamu
    -1.48
     $_{\
    -1.44
     pequena
    -1.43
    {
    -1.40
     {
    -1.40
     $_{
    -1.38
     for
    -1.38
     \
    -1.37
    POSITIVE LOGITS
    ttino
    1.63
    ㉗
    1.47
    ();)
    1.47
    卻
    1.44
     expresses
    1.43
    泱
    1.43
    閬
    1.42
    ས།
    1.41
     стреми
    1.41
    涪
    1.41
    Activations Density 0.008%

    No Known Activations