© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84327
    Prev
    Next
    INDEX
    Explanations

    UI components and code

    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
     muualla
    -1.05
     були
    -0.96
    iteľ
    -0.92
     artikke
    -0.87
    公式サイト
    -0.86
     Arquitectura
    -0.85
     garota
    -0.84
    )：
    -0.82
    łec
    -0.82
    žité
    -0.82
    POSITIVE LOGITS
    still
    1.03
     vẫn
    0.89
    STILL
    0.85
    rmse
    0.84
     ainda
    0.84
    issi
    0.82
    ঠ
    0.82
     style
    0.80
    both
    0.80
     sill
    0.80
    Activations Density 0.001%

    No Known Activations