© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87122
    Prev
    Next
    INDEX
    Explanations

    values

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

    The neuron fires on code tokens that manipulate “custom option” values (e.g. references to custom option, value, remove, product, etc.), i.e. code handling product custom‐option parameters.

    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
    iç
    -0.79
     کیلوم
    -0.76
    Dans
    -0.75
     Blat
    -0.75
    籍
    -0.73
     zám
    -0.72
     nehme
    -0.72
     Opportun
    -0.71
    łaś
    -0.71
     Poet
    -0.69
    POSITIVE LOGITS
     values
    1.41
     значения
    1.09
    values
    1.09
     value
    1.06
    值的
    1.05
     Values
    1.03
    Values
    1.02
     Value
    0.96
     valeurs
    0.94
    VALUES
    0.90
    Activations Density 0.014%

    No Known Activations