© 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. 117782
    Prev
    Next
    INDEX
    Explanations

    HTML and code headers

    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
     even
    -0.96
     this
    -0.93
     that
    -0.88
     it
    -0.84
     featuring
    -0.82
    ERI
    -0.81
    第七
    -0.81
     helps
    -0.80
    اعات
    -0.78
     aimed
    -0.77
    POSITIVE LOGITS
     personnalisés
    0.87
     réglable
    0.82
     modernes
    0.81
     originaux
    0.80
     تفاوت
    0.80
    öffentlichung
    0.79
    therly
    0.79
     توضی
    0.79
     aislamiento
    0.79
    看得
    0.78
    Activations Density 0.025%

    No Known Activations