© 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. 57140
    Prev
    Next
    INDEX
    Explanations

    API authentication errors

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

    The main thing this neuron does is detect numeric tokens (multi‐digit numbers and codes) in the text.

    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
     تجه
    -0.88
    しか
    -0.82
     joan
    -0.81
     ekster
    -0.80
    Herald
    -0.79
     tuh
    -0.77
     tdi
    -0.76
     momen
    -0.76
     tew
    -0.75
     ude
    -0.75
    POSITIVE LOGITS
     request
    0.88
     serving
    0.81
    vary
    0.80
    炊き
    0.79
     nonzero
    0.75
    Vary
    0.74
    trace
    0.73
     victorious
    0.73
     weary
    0.72
     proceso
    0.72
    Activations Density 0.019%

    No Known Activations