© 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. 99170
    Prev
    Next
    INDEX
    Explanations

    copyright notices and code structures

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

    The neuron flags tokens that look like formal identifiers or names—especially capitalized code or XML names and similar named tokens.

    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
    auer
    -0.84
     removing
    -0.78
    析
    -0.77
    Injured
    -0.77
    örungen
    -0.77
    ❜
    -0.75
     mines
    -0.73
    ="<
    -0.73
    lasty
    -0.71
    ený
    -0.71
    POSITIVE LOGITS
     Array
    1.16
     array
    1.11
    数组
    1.05
    Array
    1.00
     배
    0.98
     Arrays
    0.92
     arrays
    0.90
    array
    0.88
     Hack
    0.82
    长度
    0.82
    Activations Density 0.001%

    No Known Activations