© 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. 79152
    Prev
    Next
    INDEX
    Explanations

    specific domains and concepts

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

    The neuron fires on infrequent, content-bearing words—i.e. technical or domain-specific keywords rather than common function words.

    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
    憫
    -1.02
    likelihood
    -1.01
    Campeonato
    -0.99
     Though
    -0.98
    intree
    -0.96
    Though
    -0.96
    もあった
    -0.95
    splitContainer
    -0.94
    担忧
    -0.94
    tellten
    -0.93
    POSITIVE LOGITS
     the
    2.66
     ​​
    1.09
     differentiated
    1.06
    最も
    1.03
    ᴎ
    1.01
     аксессу
    0.99
    /></
    0.98
    大丈夫です
    0.97
     analyzes
    0.96
     ミニ
    0.96
    Activations Density 0.124%

    No Known Activations