© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62586
    Prev
    Next
    INDEX
    Explanations

    national identity, politics, or rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ਰ
    0.45
    את
    0.44
     stratification
    0.43
     दोपहर
    0.43
    انی
    0.43
    பட
    0.43
    נ
    0.43
     desesper
    0.41
    ல்ல
    0.41
    篤
    0.41
    POSITIVE LOGITS
     Finnish
    0.48
     Ph
    0.45
     touring
    0.45
     Touring
    0.43
     व्यव
    0.42
    Ph
    0.42
     gingham
    0.41
     historique
    0.41
    ụ
    0.41
    TAG
    0.40
    Activations Density 0.007%

    No Known Activations