© 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. 10-GEMMASCOPE-RES-131K
    7. 129170
    Prev
    Next
    INDEX
    Explanations

    command-line arguments

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

    The neuron activates on occurrences of the double-asterisk (“**”) pointer operator, i.e. multi‐level pointer declarations.

    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
     \
    -2.08
    alamus
    -1.73
     and
    -1.69
    geſ
    -1.65
    amaño
    -1.63
     to
    -1.63
     żeby
    -1.56
     když
    -1.52
    VIATIONS
    -1.51
    <em>
    -1.48
    POSITIVE LOGITS
    啊啊
    1.91
     Including
    1.88
    including
    1.84
    Spesifikasi
    1.73
     êtres
    1.72
    阋
    1.72
    糁
    1.70
    ława
    1.66
    ść
    1.62
    Setiap
    1.60
    Activations Density 0.007%

    No Known Activations