© 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. 256058
    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
    s
    0.63
    f
    0.50
    ో
    0.50
    dust
    0.47
    ol
    0.46
    pez
    0.46
    akl
    0.46
    Cl
    0.46
    V
    0.45
     reducer
    0.45
    POSITIVE LOGITS
    ềm
    0.50
    ۔
    0.50
     pensamento
    0.49
     ciudades
    0.48
     xong
    0.47
    تهای
    0.47
     mily
    0.46
    ட்டி
    0.46
     arus
    0.45
     Антон
    0.45
    Activations Density 0.001%

    No Known Activations