© 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. 66434
    Prev
    Next
    INDEX
    Explanations

    directed ortho, directed graph, directive

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

    The neuron fires on occurrences of the root “direct,” including inflected forms and derivatives like direct, directing, directed, and directive.

    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
     verurs
    -2.48
    鯷
    -2.30
    隽
    -2.19
    ꙁ
    -2.19
     малень
    -2.14
     umumnya
    -2.13
    O
    -2.11
    鑷
    -2.09
    ğına
    -2.08
     dasarnya
    -2.08
    POSITIVE LOGITS
    .
    2.73
     The
    2.61
     onze
    2.50
     '
    2.48
     Externe
    2.33
    ";
    2.31
     bedien
    2.28
     permita
    2.23
     münchen
    2.22
    ⪧
    2.16
    Activations Density 0.077%

    No Known Activations