© 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. 33505
    Prev
    Next
    INDEX
    Explanations

    license

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

    This neuron responds strongly to long, multi-syllable technical or formal terms.

    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
     spion
    -0.76
    LinkedIn
    -0.76
     reden
    -0.75
     Breeding
    -0.74
     elas
    -0.71
     tragically
    -0.70
    ֶּ
    -0.70
    Dopo
    -0.69
     Gep
    -0.68
     interminable
    -0.67
    POSITIVE LOGITS
    で見る
    0.76
    훗
    0.73
     Barth
    0.71
     solve
    0.69
    IdList
    0.69
    thumbsup
    0.69
     Mansfield
    0.68
     એ
    0.68
    dles
    0.68
     Solve
    0.68
    Activations Density 0.014%

    No Known Activations