© 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. 10-GEMMASCOPE-RES-131K
    7. 40324
    Prev
    Next
    INDEX
    Explanations

    connects or replaces

    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_10/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
    órios
    -1.05
     بهترین
    -1.03
     exhortation
    -1.02
     jamur
    -1.02
    ening
    -1.00
    ು
    -0.99
     takiego
    -0.98
    𝗶
    -0.97
    to
    -0.96
    ApiProperty
    -0.96
    POSITIVE LOGITS
     worse
    1.30
     not
    1.27
     but
    1.23
     koste
    1.16
     it
    1.16
     none
    1.13
     latter
    1.13
    wahati
    1.12
     we
    1.11
     lekk
    1.11
    Activations Density 0.137%

    No Known Activations