© 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. 34-GEMMASCOPE-RES-131K
    7. 109065
    Prev
    Next
    INDEX
    Explanations

    one of X

    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
    Some
    -1.38
    這個
    -1.30
    了一个
    -1.29
    部分
    -1.25
     what
    -1.24
    一個
    -1.19
     it
    -1.16
     всі
    -1.13
     Some
    -1.12
    其他
    -1.12
    POSITIVE LOGITS
     the
    2.05
     flera
    1.48
     two
    1.38
     tylko
    1.34
     flere
    1.30
     mehreren
    1.30
     két
    1.22
     två
    1.22
     plusieurs
    1.20
     many
    1.16
    Activations Density 0.045%

    No Known Activations