© 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. 14545
    Prev
    Next
    INDEX
    Explanations

    Q: hey, Zaïde

    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_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
     continuar
    -1.97
    i
    -1.95
    訁
    -1.94
    癭
    -1.94
     количество
    -1.86
     którzy
    -1.84
     unui
    -1.76
     impuestos
    -1.73
     certainement
    -1.73
     gdyby
    -1.72
    POSITIVE LOGITS
     新款
    1.83
    𖥧
    1.70
    嵎
    1.67
    medriver
    1.65
     夾
    1.63
    迳
    1.62
    }
    1.60
    Está
    1.59
     verdi
    1.55
     帶
    1.53
    Activations Density 0.002%

    No Known Activations