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. 8359
    Prev
    Next
    INDEX
    Explanations

    street, university, or biographical information

    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
    ikum
    -0.81
     interchang
    -0.80
    ско
    -0.77
     GME
    -0.76
    と思いました
    -0.75
    かというと
    -0.75
     зда
    -0.73
     instead
    -0.73
     Mose
    -0.72
     practi
    -0.71
    POSITIVE LOGITS
    の方に
    0.96
    ૮
    0.89
     favorites
    0.89
    roben
    0.85
    옛
    0.85
     문
    0.84
    mathsf
    0.80
     smile
    0.79
     loves
    0.78
    orges
    0.78
    Activations Density 0.003%

    No Known Activations