© 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. 60520
    Prev
    Next
    INDEX
    Explanations

    questions and statements

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

    The neuron activates on standalone numeric tokens (e.g. floating-point or integer values) that represent metadata or metrics rather than normal 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
     also
    -1.70
    *
    -1.70
    \
    -1.69
     then
    -1.63
    "
    -1.59
     this
    -1.55
     another
    -1.55
    =
    -1.54
     otra
    -1.49
     said
    -1.43
    POSITIVE LOGITS
    женская
    1.57
     alcuni
    1.54
    Ꮟ
    1.52
    まずは
    1.48
    lás
    1.47
    França
    1.45
     algunos
    1.43
    structura
    1.41
    vestidos
    1.41
    まず
    1.41
    Activations Density 0.079%

    No Known Activations