© 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. 47518
    Prev
    Next
    INDEX
    Explanations

    questions or learning environments

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

    The neuron is strongly activated by long uppercase or mixed‐case alphanumeric tokens (e.g., acronyms, code or license identifiers).

    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
     SMO
    -0.78
     Meine
    -0.75
    eBook
    -0.71
     parlamento
    -0.71
     stron
    -0.70
     VEND
    -0.70
     Luciano
    -0.70
     Sankt
    -0.69
    poss
    -0.68
     Blak
    -0.68
    POSITIVE LOGITS
     curriculum
    1.01
     environments
    0.94
     environment
    0.85
     Environments
    0.84
    Safety
    0.83
     curricula
    0.82
    Curriculum
    0.82
     safety
    0.81
    rl
    0.81
     reward
    0.79
    Activations Density 0.017%

    No Known Activations