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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130292
    Prev
    Next
    INDEX
    Explanations

    original names and titles

    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_22/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
     szinte
    -0.83
    </u>
    -0.81
     significantly
    -0.80
     class
    -0.75
     Quote
    -0.75
    ために
    -0.75
    СО
    -0.75
    sbericht
    -0.74
    interpre
    -0.73
     日本
    -0.73
    POSITIVE LOGITS
     name
    1.61
     names
    1.30
    的名字
    1.26
     moniker
    1.24
     नाम
    1.12
     rename
    1.09
    칭
    1.09
    name
    1.09
     navnet
    1.08
     secas
    1.05
    Activations Density 0.172%

    No Known Activations