© 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. 10-GEMMASCOPE-RES-131K
    7. 70965
    Prev
    Next
    INDEX
    Explanations

    templates

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

    This neuron activates on mentions of “template” (including its plural form “templates”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    2
    -2.45
    }
    -2.39
    s
    -2.39
    3
    -2.11
    o
    -2.11
    </td>
    -2.09
     I
    -2.02
     Virtually
    -1.98
     .
    -1.97
    7
    -1.97
    POSITIVE LOGITS
     også
    2.48
    퐹
    2.27
    目前的
    2.27
    垍
    2.13
     cread
    2.13
    šní
    2.08
    釭
    1.97
     colectivos
    1.92
     typy
    1.92
     направлении
    1.92
    Activations Density 0.008%

    No Known Activations