© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51356
    Prev
    Next
    INDEX
    Explanations

    ethical actions, karma, exploitation, imperialism

    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_31_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
     Fear
    0.40
    Fear
    0.39
     uncontrollable
    0.38
     చా
    0.38
     Expenditure
    0.38
     sagging
    0.38
    囱
    0.38
     Poverty
    0.38
     Advertising
    0.37
    Advertising
    0.37
    POSITIVE LOGITS
     कित
    0.42
     wronged
    0.42
     ethically
    0.41
     crimes
    0.40
     ethical
    0.40
    deeds
    0.39
     ethics
    0.39
     restitution
    0.39
     wrongs
    0.39
    鲇
    0.39
    Activations Density 0.049%

    No Known Activations