© 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. 34-GEMMASCOPE-RES-131K
    7. 91441
    Prev
    Next
    INDEX
    Explanations

    Naturals, estate, promis, Stor, Scriptable, service, imaginar

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

    This neuron fires on unusually long identifier‐ or path‐like tokens—e.g. long import paths or multi­word code symbols.

    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
    TOM
    -0.85
     dispozici
    -0.81
     If
    -0.79
    dispatchEvent
    -0.79
    бно
    -0.78
    卖
    -0.76
    震
    -0.76
     privilégi
    -0.75
    If
    -0.74
    preco
    -0.74
    POSITIVE LOGITS
    eable
    0.93
    膵
    0.92
    setIs
    0.86
     позволит
    0.81
    __:
    0.79
    ^{*
    0.79
    ギター
    0.78
    lève
    0.77
    怎么回事
    0.77
     agreed
    0.76
    Activations Density 0.117%

    No Known Activations