© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34671
    Prev
    Next
    INDEX
    Explanations

    Attribution and parenthetical citations

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

    The neuron activates on numeric tokens (years, image/photo IDs, counts, and other numbers).

    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
    <eos>
    -1.02
     }^{*}
    -0.96
     E
    -0.93
    𝐧
    -0.88
     This
    -0.88
     Have
    -0.87
    ())),
    -0.85
    equalTo
    -0.84
     S
    -0.83
    ;';
    -0.82
    POSITIVE LOGITS
     bună
    1.01
    seitigen
    0.97
    SOU
    0.97
     différentes
    0.91
    ProcessEvent
    0.91
    notre
    0.91
     détruire
    0.90
     protège
    0.90
    clases
    0.90
    Cambo
    0.89
    Activations Density 0.023%

    No Known Activations