© 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. 257890
    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
     behavi
    0.49
    坦
    0.46
    rieren
    0.45
     professional
    0.45
    C
    0.45
     Type
    0.44
    Ĭ
    0.44
    World
    0.43
    (
    0.43
     Ogden
    0.42
    POSITIVE LOGITS
    níků
    0.51
     Idani
    0.47
    kona
    0.47
    きた
    0.46
     daleko
    0.46
    iak
    0.46
    يي
    0.45
    NSDictionary
    0.44
    itiva
    0.44
    nič
    0.44
    Activations Density 0.001%

    No Known Activations