© 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. 259553
    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
    ilik
    0.40
    ed
    0.40
    inz
    0.40
    -
    0.39
     validated
    0.39
    カリ
    0.39
     Description
    0.39
    特殊
    0.38
     भरी
    0.38
    aus
    0.38
    POSITIVE LOGITS
     участке
    0.60
     为了
    0.55
     механизм
    0.54
     让
    0.51
     把
    0.51
    ட்டால்
    0.49
     然而
    0.49
     அதில்
    0.48
     ذریعے
    0.47
     случае
    0.47
    Activations Density 0.000%

    No Known Activations