© 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. 66872
    Prev
    Next
    INDEX
    Explanations

    items needed or some

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

    This neuron detects the parts of instructional or how-to text that list required materials, tools, or supplies (e.g. “you’ll need,” “need,” or “is required”).

    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
     more
    -1.73
    ↵
    -1.67
     ‘
    -1.59
    which
    -1.55
    ‘
    -1.54
    u
    -1.52
     over
    -1.44
    ’
    -1.44
     all
    -1.42
    _
    -1.42
    POSITIVE LOGITS
     okam
    1.53
     rafraî
    1.50
     jednom
    1.47
    ᛬
    1.45
     goû
    1.45
     diinginkan
    1.43
     tajem
    1.38
     reklama
    1.37
     ženy
    1.34
    dikan
    1.32
    Activations Density 0.033%

    No Known Activations