© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31017
    Prev
    Next
    INDEX
    Explanations

    model syntax with arrows

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

    The neuron flags technical “tokens” such as variable names, numeric literals, or symbol commands (e.g. backslashes in LaTeX, model identifiers, digits) typical of math or code snippets.

    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
     ↔
    -1.30
    leftrightarrow
    -1.24
     <=>
    -1.13
    ↔
    -1.13
    ⇔
    -1.02
     ←
    -0.99
    Leftrightarrow
    -0.95
    <=
    -0.87
    <-
    -0.82
     <-
    -0.80
    POSITIVE LOGITS
    》
    0.84
     kacang
    0.80
    .^
    0.79
    ∁
    0.77
     parfait
    0.77
     Clipboard
    0.76
     cetera
    0.75
    hanging
    0.75
    Lugares
    0.74
     institu
    0.73
    Activations Density 0.037%

    No Known Activations