© 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. 91398
    Prev
    Next
    INDEX
    Explanations

    numbers and slashes

    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
     such
    -1.19
     an
    -1.15
     each
    -1.05
     while
    -1.03
     one
    -0.94
     sizable
    -0.94
     moderately
    -0.94
     prominent
    -0.93
     substantial
    -0.90
     contemplar
    -0.90
    POSITIVE LOGITS
     yyr
    1.20
     bunt
    1.14
    闼
    1.09
     האָ
    1.02
     formid
    1.01
     машину
    1.01
    runtime
    1.00
    dinger
    0.96
    plt
    0.96
    годно
    0.96
    Activations Density 0.123%

    No Known Activations