© 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. 85510
    Prev
    Next
    INDEX
    Explanations

    tutorials and instructions

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

    The main thing this neuron does is spot explicit references to tutorials or instructional resources (e.g. “tutorial,” “tuto,” or URLs/brands like Instructables).

    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
     \
    -1.70
     all
    -1.58
     F
    -1.52
    ),
    -1.49
     .
    -1.46
     two
    -1.41
     sehr
    -1.39
     A
    -1.36
     three
    -1.36
     non
    -1.33
    POSITIVE LOGITS
    躥
    1.55
     poë
    1.48
     Ucraina
    1.45
    翃
    1.43
     poils
    1.41
     hjemmeside
    1.38
     luy
    1.38
     witte
    1.37
     groote
    1.36
     spil
    1.36
    Activations Density 0.073%

    No Known Activations