© 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. 90951
    Prev
    Next
    INDEX
    Explanations

    wrist strap

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

    The neuron fires strongly on text full of product‐specification or promotional language—e.g. detailed, technical–style descriptions of items (like watch features).

    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
    YP
    -0.82
    rupt
    -0.78
     lett
    -0.75
     Fing
    -0.75
    bolt
    -0.75
     negotiation
    -0.75
     Ename
    -0.75
     mascara
    -0.71
     Finlandia
    -0.71
    SOA
    -0.71
    POSITIVE LOGITS
     strap
    1.94
     straps
    1.68
     band
    1.63
    band
    1.40
    バンド
    1.30
    Band
    1.29
     bands
    1.29
     реме
    1.27
     Strap
    1.27
     Band
    1.22
    Activations Density 0.009%

    No Known Activations