© 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. 115725
    Prev
    Next
    INDEX
    Explanations

    invention relates to

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

    The neuron is essentially a detector for the literal token “false” in code.

    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
    пози
    -0.87
    uestamente
    -0.86
    чью
    -0.84
    Yesterday
    -0.83
    <0xF0>
    -0.83
    ⌜
    -0.83
     Kristus
    -0.80
     kalori
    -0.78
    نح
    -0.78
    失礼
    -0.78
    POSITIVE LOGITS
     ebenso
    1.00
    klá
    0.95
    </tr>
    0.93
     anderes
    0.91
     hierbei
    0.84
     vieles
    0.82
     burada
    0.82
     direttamente
    0.80
    ccional
    0.79
    oner
    0.79
    Activations Density 0.001%

    No Known Activations