© 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. 22-GEMMASCOPE-RES-131K
    7. 65684
    Prev
    Next
    INDEX
    Explanations

    output or result

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

    This neuron fires on mentions of “output” (especially uppercase OUT) or related output‐file/variable names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     acostumb
    -1.03
     ਅਤੇ
    -1.03
    aterdag
    -1.01
    誹
    -1.01
    hipster
    -0.97
    oggi
    -0.97
     xadrez
    -0.96
     сейчас
    -0.95
    andidat
    -0.93
    gunakan
    -0.93
    POSITIVE LOGITS
    p
    0.94
    ER
    0.94
    viève
    0.93
    𝗠
    0.91
    bitur
    0.90
    izado
    0.89
    };*/
    0.88
    Generation
    0.88
    Verification
    0.88
    リ
    0.88
    Activations Density 0.049%

    No Known Activations