© 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. 10-GEMMASCOPE-RES-131K
    7. 85476
    Prev
    Next
    INDEX
    Explanations

    fade in/out animation

    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
    鹚
    -2.55
    啬
    -2.41
     admirable
    -2.41
    udades
    -2.36
    洨
    -2.33
    轳
    -2.30
     evolving
    -2.25
    ми
    -2.25
    li
    -2.25
     находя
    -2.22
    POSITIVE LOGITS
    e
    3.11
     -----
    2.59
    --
    2.58
     ----
    2.45
    是非常
    2.39
    able
    2.39
     mehrere
    2.27
    c
    2.23
    是個
    2.23
     قبل
    2.23
    Activations Density 0.005%

    No Known Activations