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. 8117
    Prev
    Next
    INDEX
    Explanations

    stone's throw and proximity

    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
    Loads
    -0.81
    婦人
    -0.81
    Wrk
    -0.77
    irme
    -0.77
     Learned
    -0.77
    reciate
    -0.75
    もちゃ
    -0.75
    vestidos
    -0.73
    quanti
    -0.71
     geweldig
    -0.70
    POSITIVE LOGITS
     stone
    2.36
     stones
    2.23
     hop
    1.66
    stone
    1.58
     hair
    1.38
    Stone
    1.38
    石
    1.37
    stones
    1.32
     whis
    1.31
     short
    1.24
    Activations Density 0.015%

    No Known Activations