© 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. 63982
    Prev
    Next
    INDEX
    Explanations

    words starting with Sm

    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
    \]
    -0.75
    Subtract
    -0.73
    odom
    -0.71
    abuse
    -0.68
    Premium
    -0.68
    Rooms
    -0.68
    Lux
    -0.67
    mayr
    -0.67
    slf
    -0.67
    に近い
    -0.66
    POSITIVE LOGITS
     SMA
    1.12
     Sme
    1.11
    Sme
    1.04
    sme
    0.98
     sme
    0.94
     SME
    0.88
     Martens
    0.85
     smear
    0.84
    SMA
    0.84
     mə
    0.77
    Activations Density 0.028%

    No Known Activations