© 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. 44687
    Prev
    Next
    INDEX
    Explanations

    tangent to

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

    The neuron is specialized in spotting occurrences of the “tang-” root (e.g. tangent, tangential, tangentially, etc.) in the text.

    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
    untuk
    -2.13
    蹓
    -2.02
    」
    -1.95
    ⢊
    -1.89
    Capacidad
    -1.88
     Obat
    -1.85
    cuando
    -1.84
     vermek
    -1.83
    𝔗
    -1.81
    ’:
    -1.74
    POSITIVE LOGITS
    "
    2.27
     of
    2.14
     For
    2.06
    '
    2.05
    \
    2.03
     know
    1.77
     time
    1.75
    ।
    1.72
     as
    1.69
    ﾍ
    1.64
    Activations Density 0.009%

    No Known Activations