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. 8499
    Prev
    Next
    INDEX
    Explanations

    rocks and stones

    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
    óngase
    -0.96
    issants
    -0.82
     timberland
    -0.81
     sawmill
    -0.81
    čkou
    -0.80
     greenhouses
    -0.79
    ְּ
    -0.78
     swamps
    -0.76
    antası
    -0.74
    ɰ
    -0.74
    POSITIVE LOGITS
     rocks
    4.28
     rock
    4.00
     stones
    3.30
     stone
    3.16
    rock
    3.05
    rocks
    2.91
     Rocks
    2.91
     Rock
    2.70
    Rocks
    2.69
    ROCK
    2.63
    Activations Density 0.055%

    No Known Activations