© 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. 59485
    Prev
    Next
    INDEX
    Explanations

    lists of numbers and characters

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

    This neuron never activates on any of the tokens—it appears to be effectively “dead” in these examples.

    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
    venir
    -0.83
    વે
    -0.79
    řeba
    -0.79
    
    -0.77
    ouders
    -0.77
    cente
    -0.76
    Clique
    -0.75
    ень
    -0.74
    ouver
    -0.74
    paraiso
    -0.74
    POSITIVE LOGITS
    Hyd
    0.75
    wia
    0.75
    Vá
    0.75
    Hü
    0.74
     још
    0.74
     occhi
    0.73
     अगर
    0.73
    asjon
    0.71
    不知
    0.69
    hitheater
    0.69
    Activations Density 0.007%

    No Known Activations