© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 100663
    Prev
    Next
    INDEX
    Explanations

    tea shop mystery cafe Elderly

    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_all/layer_41_width_262k_l0_big
    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
    🤮
    0.61
    😈
    0.54
     propagand
    0.52
     screams
    0.52
     raping
    0.50
     enraged
    0.50
     hysteria
    0.49
     swagger
    0.49
    😵
    0.49
     атаку
    0.49
    POSITIVE LOGITS
     melanch
    0.68
     heartwarming
    0.68
     elderly
    0.66
     loneliness
    0.66
     befri
    0.66
     bittersweet
    0.65
     Healing
    0.64
     lonely
    0.63
     cafe
    0.62
     Elderly
    0.61
    Activations Density 0.000%

    No Known Activations