© 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. 65216
    Prev
    Next
    INDEX
    Explanations

    bill validators, screen capture, document feeder

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

    The neuron fires on domain-specific technical terms denoting hardware, media, or data items (e.g. “card,” “SIM,” “bill,” “image,” “tobacco,” “wire,” “RSS,” 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
     satisfecho
    -1.11
     laissant
    -1.09
    杈
    -1.07
    amaged
    -1.04
     réaliser
    -1.03
     vêtements
    -1.02
     télécharger
    -0.99
     Gehalt
    -0.98
     cheveux
    -0.98
    物が
    -0.97
    POSITIVE LOGITS
    There
    1.02
    Koordinaten
    0.98
     evaluation
    0.97
    Regardless
    0.97
     Often
    0.97
    Often
    0.96
    During
    0.95
     Regardless
    0.94
    -¿
    0.93
     retrieval
    0.91
    Activations Density 0.230%

    No Known Activations