© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54410
    Prev
    Next
    INDEX
    Explanations

    duty, responsibility, obligations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_width_262k_l0_small_affine
    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
     /ˈ
    0.36
    കൊണ്ട്
    0.34
     الشه
    0.34
     никак
    0.34
    場合に
    0.33
     nimmt
    0.33
    AssemblyName
    0.33
    Million
    0.33
    氇
    0.32
    Where
    0.32
    POSITIVE LOGITS
     duty
    0.54
     responsibility
    0.53
     duties
    0.53
     обязан
    0.47
    职责
    0.47
     обязанности
    0.46
    duty
    0.46
    responsibility
    0.46
     respons
    0.45
     responsabilità
    0.44
    Activations Density 0.007%

    No Known Activations