© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 251390
    Prev
    Next
    INDEX
    Explanations

    fronts and calligraphy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1
    0.46
    endtime
    0.42
    centage
    0.40
    ioneer
    0.40
    scanning
    0.40
    insol
    0.40
    рур
    0.39
     anemia
    0.39
    艱
    0.39
    tter
    0.38
    POSITIVE LOGITS
     منظور
    0.56
     بین
    0.52
     francesa
    0.52
     pomiędzy
    0.50
     গুলোতে
    0.50
    स्परिक
    0.48
     détail
    0.47
     francese
    0.47
     françaises
    0.47
     ברי
    0.46
    Activations Density 0.000%

    No Known Activations