© 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. 127961
    Prev
    Next
    INDEX
    Explanations

    Client, Q, Executive introductions

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

    The neuron detects capitalized technical identifiers (e.g. class or exception names) in code snippets.

    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
     and
    -2.53
     or
    -2.27
     the
    -1.64
    Crítica
    -1.48
     in
    -1.42
     at
    -1.39
    ”。
    -1.36
    Misión
    -1.35
    Visión
    -1.35
     This
    -1.34
    POSITIVE LOGITS
     позволяют
    1.73
    ᯾
    1.70
    significantly
    1.68
    ⎔
    1.60
     hilfreich
    1.59
     ܙ
    1.58
    頗
    1.58
    ︲
    1.57
     spécialement
    1.57
     %=
    1.56
    Activations Density 0.000%

    No Known Activations