© 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. 60799
    Prev
    Next
    INDEX
    Explanations

    code file extensions

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

    The neuron responds to numeric tokens (e.g. line numbers, error‐code values, file positions, CSS sizes, etc.).

    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
     "[
    -1.20
     "...
    -1.18
     its
    -1.11
    おわりに
    -0.98
     Actually
    -0.98
     it
    -0.94
    ēju
    -0.93
     ("
    -0.92
    endimento
    -0.92
     einer
    -0.91
    POSITIVE LOGITS
    そういった
    1.07
    Clicks
    1.00
    romatic
    0.99
    Instru
    0.98
    .»
    0.98
     intérêts
    0.98
    Ɇ
    0.97
    ›
    0.97
    Decorated
    0.97
    "/>
    0.96
    Activations Density 0.001%

    No Known Activations