© 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-RES-16K
    7. 9613
    Prev
    Next
    INDEX
    Explanations

    authoritarianism and dissent

    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_16k_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
    ка
    0.53
     столь
    0.53
    Luckily
    0.51
    Luca
    0.51
    So
    0.50
    ö
    0.49
    Andrew
    0.49
    Het
    0.48
    밌
    0.47
    P
    0.47
    POSITIVE LOGITS
     incarceration
    0.52
     garments
    0.52
     clothing
    0.52
     nationalist
    0.51
     imprisonment
    0.50
     slums
    0.49
     unlawful
    0.49
     analges
    0.49
     hatred
    0.48
     illiterate
    0.48
    Activations Density 0.489%

    No Known Activations