© 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. 112775
    Prev
    Next
    INDEX
    Explanations

    NLS, backends, Q:

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

    The neuron fires on uppercase technical identifiers and acronyms (e.g. config or code constants like NLS_* and BACKENDS).

    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
     otras
    -2.16
    龶
    -1.98
    ↵↵
    -1.92
    战胜
    -1.73
    chaik
    -1.73
     are
    -1.72
    𓋼
    -1.70
     entanto
    -1.69
     freaking
    -1.66
    !"
    -1.65
    POSITIVE LOGITS
    垕
    1.91
    which
    1.75
     of
    1.73
    蒾
    1.70
    ي
    1.67
    但我
    1.67
     they
    1.63
     sasa
    1.56
     生物
    1.54
    觧
    1.54
    Activations Density 0.000%

    No Known Activations