© 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. 34-GEMMASCOPE-RES-131K
    7. 32044
    Prev
    Next
    INDEX
    Explanations

    code snippets and file paths

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

    The neuron fires on standalone numeric tokens (e.g. version numbers, line numbers, dimensions, years) in code or 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_34/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
     Unii
    -0.70
     reef
    -0.65
    と思ったら
    -0.64
     concent
    -0.63
    ccedil
    -0.62
    ⌋
    -0.61
    opra
    -0.61
     Morgen
    -0.60
     Monta
    -0.60
     Gardens
    -0.59
    POSITIVE LOGITS
    Argb
    0.90
    женной
    0.73
    himi
    0.72
    вач
    0.70
     multimeter
    0.69
    frances
    0.69
     należy
    0.68
     puncak
    0.67
     издели
    0.67
    しばらく
    0.67
    Activations Density 0.091%

    No Known Activations