© 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. 259813
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    сут
    0.48
    (
    0.48
     erscheinen
    0.48
    توى
    0.48
    ضه
    0.47
    ه
    0.47
    而且
    0.46
    فيذ
    0.46
    是
    0.46
    ModelGrid
    0.45
    POSITIVE LOGITS
    modules
    0.52
     नवंबर
    0.50
    rear
    0.48
    boxing
    0.47
    दस
    0.47
    सामान्यीकृत
    0.47
     जून
    0.46
    roots
    0.46
    akaran
    0.46
    avasena
    0.44
    Activations Density 0.001%

    No Known Activations