© 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. 256557
    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
    manam
    0.52
    ೋಟ
    0.48
    ἃ
    0.48
     PHILLIPS
    0.47
     диагностики
    0.47
    𝗄
    0.47
     OBJECTTYPE
    0.46
    ресень
    0.45
    सबुक
    0.44
    孃
    0.44
    POSITIVE LOGITS
     tobacco
    0.49
    رياض
    0.49
     e
    0.47
    group
    0.46
     folosit
    0.46
     can
    0.46
     dupa
    0.46
    out
    0.46
     elong
    0.45
     deputy
    0.44
    Activations Density 0.000%

    No Known Activations