© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93948
    Prev
    Next
    INDEX
    Explanations

    accounts for percentages

    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
    amerikanischer
    -0.94
     there
    -0.92
     many
    -0.90
    tadora
    -0.88
    There
    -0.86
    Many
    -0.85
     people
    -0.85
    Some
    -0.85
    hithe
    -0.84
     same
    -0.82
    POSITIVE LOGITS
     accounted
    1.63
     account
    1.45
     accounting
    1.30
     accounts
    1.22
     полови
    1.15
     chiếm
    1.13
    account
    1.11
     lion
    1.07
     ACCOUNT
    1.05
     HALF
    1.05
    Activations Density 0.057%

    No Known Activations