© 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. 66222
    Prev
    Next
    INDEX
    Explanations

    value of parameters or variables

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

    The neuron fires on numeric tokens (i.e. numbers) in the 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
    aragua
    -0.96
    idenav
    -0.92
     basée
    -0.85
    ąc
    -0.85
     zwem
    -0.85
     mockup
    -0.85
    Subgoals
    -0.84
     VAS
    -0.82
    煽
    -0.82
    thschild
    -0.82
    POSITIVE LOGITS
     each
    1.27
     variables
    1.25
     parameter
    1.10
     parameters
    1.05
     at
    0.96
    variables
    0.93
     Parameters
    0.92
     the
    0.91
     for
    0.90
    parameters
    0.87
    Activations Density 0.056%

    No Known Activations