© 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. 34-GEMMASCOPE-RES-131K
    7. 93615
    Prev
    Next
    INDEX
    Explanations

    may or might be

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

    The neuron detects boilerplate notices about archived articles and their potentially outdated information.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ミ
    -0.86
    据
    -0.82
     hinein
    -0.80
    mavi
    -0.76
    clair
    -0.76
    say
    -0.74
     Theolog
    -0.73
    pertoire
    -0.73
     خاصی
    -0.72
     Yves
    -0.72
    POSITIVE LOGITS
     ممکن
    2.64
     might
    2.14
     may
    2.13
     может
    2.02
     може
    1.98
     mungkin
    1.98
    可能
    1.95
     possible
    1.91
     peut
    1.72
     lehet
    1.69
    Activations Density 0.034%

    No Known Activations