© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63203
    Prev
    Next
    INDEX
    Explanations

    smooth support

    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
     комп
    -0.74
     Bohemia
    -0.71
     Boko
    -0.71
     elders
    -0.71
    इ
    -0.69
    Elder
    -0.68
     Garnett
    -0.68
     Scud
    -0.67
     clerk
    -0.67
    𝜆
    -0.67
    POSITIVE LOGITS
     support
    1.17
     Support
    1.16
     supports
    1.12
     compact
    1.09
    support
    1.09
     SUPPORT
    1.06
     test
    1.05
     smooth
    1.02
    smooth
    1.00
     Smooth
    0.99
    Activations Density 0.021%

    No Known Activations