© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115955
    Prev
    Next
    INDEX
    Explanations

    `INCLUDED`

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

    The neuron fires on code tokens that end with numeric suffixes—i.e. identifiers or macros containing underscores followed by digits.

    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
     by
    -0.77
     forecasts
    -0.73
     Stanley
    -0.73
    侖
    -0.73
     italia
    -0.73
     may
    -0.73
     pizz
    -0.71
     stanley
    -0.70
     which
    -0.69
    :^(
    -0.69
    POSITIVE LOGITS
     ausgeführt
    1.02
    明日は
    0.90
     ilyen
    0.90
    ***
    0.87
    cribir
    0.86
    ****
    0.86
    ごめん
    0.85
    ====
    0.85
     متن
    0.84
    いっ
    0.84
    Activations Density 0.002%

    No Known Activations