© 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. 38198
    Prev
    Next
    INDEX
    Explanations

    iteration with index

    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
     chce
    -0.88
     AÑOS
    -0.86
     }}=\
    -0.82
    ünüz
    -0.80
     those
    -0.77
    ümü
    -0.77
    undan
    -0.76
    utch
    -0.76
     veroor
    -0.76
    Pen
    -0.76
    POSITIVE LOGITS
     очеред
    0.98
     each
    0.95
    enetic
    0.87
    Each
    0.86
     также
    0.85
     Each
    0.82
    Каждый
    0.81
    continue
    0.79
     Fic
    0.79
     myös
    0.78
    Activations Density 0.017%

    No Known Activations