© 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. 127933
    Prev
    Next
    INDEX
    Explanations

    Victoria's Secret

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

    The neuron strongly activates on Turkish word endings and inflectional suffixes (i.e. Turkish morphological markers).

    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
     forKey
    -2.34
    埽
    -2.09
     whoſe
    -2.00
    硨
    -1.99
    ⬮
    -1.96
     you
    -1.96
    鷓
    -1.95
    ᯾
    -1.94
    ⬈
    -1.84
    秾
    -1.82
    POSITIVE LOGITS
     Näch
    2.48
    焄
    2.23
     Another
    2.00
     another
    1.95
    就是一个
    1.93
     more
    1.89
     自動
    1.83
     During
    1.82
    Ꮽ
    1.82
     剤
    1.77
    Activations Density 0.003%

    No Known Activations