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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8331
    Prev
    Next
    INDEX
    Explanations

    hanging wall art

    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
     июля
    -0.87
    ших
    -0.83
    FlatAppearance
    -0.81
     mounds
    -0.81
    킹
    -0.77
     sculpting
    -0.77
    Structures
    -0.75
     handheld
    -0.74
     slutet
    -0.74
    vestream
    -0.73
    POSITIVE LOGITS
     wall
    2.84
     hanging
    2.48
     hung
    2.47
    hung
    2.28
     framed
    2.25
    wall
    2.19
     hangs
    2.08
    Hanging
    2.02
     hang
    2.02
     hanged
    1.98
    Activations Density 0.037%

    No Known Activations