© 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. 22-GEMMASCOPE-RES-131K
    7. 33608
    Prev
    Next
    INDEX
    Explanations

    mathematical and code syntax

    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_22/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
    的感覺
    -0.86
     Bretaña
    -0.86
     روسیه
    -0.85
    ıllı
    -0.79
     health
    -0.79
     zdravot
    -0.79
    的時候
    -0.77
     saúde
    -0.77
    پزخانه
    -0.77
    iální
    -0.76
    POSITIVE LOGITS
     dosen
    0.91
     retards
    0.84
    hér
    0.84
    août
    0.82
     until
    0.82
     Pati
    0.81
     recogn
    0.79
    က်
    0.79
     untill
    0.77
     Personne
    0.77
    Activations Density 0.022%

    No Known Activations