© 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. 34-GEMMASCOPE-RES-131K
    7. 78875
    Prev
    Next
    INDEX
    Explanations

    US place names and counties

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Рейтинг
    -0.79
     wyłącznie
    -0.76
     չ
    -0.75
    Secs
    -0.74
     messen
    -0.71
    堀
    -0.71
    图片来源
    -0.70
     стоимо
    -0.70
    ıştır
    -0.69
     garde
    -0.68
    POSITIVE LOGITS
    algunos
    0.85
     Grenada
    0.84
     Sardinia
    0.80
    kozá
    0.78
     Yankees
    0.77
    ]"
    0.77
     injective
    0.76
    存款
    0.75
     veno
    0.75
     Courthouse
    0.75
    Activations Density 0.025%

    No Known Activations