© 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. 256581
    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
     Mere
    0.46
    }]}
    0.44
    جاد
    0.43
    ש
    0.42
     Cred
    0.42
     Sign
    0.42
     Adoption
    0.41
     اس
    0.41
     Text
    0.41
    ال
    0.40
    POSITIVE LOGITS
    ween
    0.62
    aré
    0.62
     විශ
    0.55
    úc
    0.52
     кандидат
    0.52
    ύ
    0.52
    erva
    0.51
    árm
    0.51
    ’
    0.51
     deine
    0.50
    Activations Density 0.000%

    No Known Activations