© 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. 31264
    Prev
    Next
    INDEX
    Explanations

    does not make sense

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

    This neuron detects the “does not contain a <something>” phrasing used in error messages.

    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
     somewhat
    -1.73
     nothing
    -1.51
     некото
    -1.50
    somewhat
    -1.41
    ไม่มี
    -1.41
     både
    -1.34
    nothing
    -1.34
    ไม่
    -1.29
     nejen
    -1.25
    不仅
    -1.22
    POSITIVE LOGITS
     any
    4.34
     anything
    3.56
     anymore
    3.39
    任何
    2.72
     nor
    2.69
    有任何
    2.64
     anywhere
    2.52
     anyone
    2.48
     אלא
    2.25
     anybody
    2.23
    Activations Density 0.139%

    No Known Activations