© 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. 73633
    Prev
    Next
    INDEX
    Explanations

    door parts and surfaces

    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
    の方に
    -0.93
     пти
    -0.88
    ক্ত
    -0.87
    側の
    -0.86
     amorosa
    -0.81
    uatu
    -0.79
     tolerancia
    -0.74
     elongated
    -0.74
     Angular
    -0.74
    leurs
    -0.74
    POSITIVE LOGITS
     edges
    1.19
     surface
    1.14
     edge
    1.07
     söyledi
    1.05
     margin
    1.05
    べ
    1.04
     forefront
    1.00
    edges
    0.98
     surfaces
    0.98
     periphery
    0.97
    Activations Density 0.216%

    No Known Activations