© 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. 258606
    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
    were
    0.51
    bodied
    0.49
    picked
    0.49
    今回の
    0.48
    {(-
    0.48
    parts
    0.45
     Rā
    0.45
    vinced
    0.45
     theſe
    0.45
    ўным
    0.45
    POSITIVE LOGITS
     permettant
    0.47
    抚
    0.47
    徜
    0.46
    TH
    0.45
     c
    0.44
    ंदगी
    0.44
    借鉴
    0.42
     restoran
    0.42
    🍖
    0.42
    จน
    0.41
    Activations Density 0.001%

    No Known Activations