Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8496
    Prev
    Next
    INDEX
    Explanations

    physical closeness and warmth

    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
    Buckets
    -0.81
     Bypass
    -0.78
    specular
    -0.75
     गां
    -0.75
    ಗೆ
    -0.75
    ervis
    -0.73
    temporada
    -0.72
     Imagery
    -0.71
    ailles
    -0.71
     mercy
    -0.71
    POSITIVE LOGITS
     nu
    1.48
     snug
    1.41
     bury
    1.31
     burying
    1.29
     nest
    1.19
     cling
    1.13
     buried
    1.09
     closeness
    1.06
     against
    1.05
     warm
    1.02
    Activations Density 0.007%

    No Known Activations