© 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. 16-GEMMASCOPE-2-RES-262K
    7. 118530
    Prev
    Next
    INDEX
    Explanations

    ethical and other concepts

    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_16_width_262k_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
    itas
    0.54
    TO
    0.52
    ции
    0.50
     рода
    0.49
    তা
    0.48
    )”
    0.48
    Pooling
    0.48
    )">
    0.47
    دارة
    0.47
    يو
    0.46
    POSITIVE LOGITS
    ҷи
    0.55
    邀請
    0.52
    ವಾಡ
    0.52
    otherm
    0.51
     Severn
    0.50
    gus
    0.49
    ્વ
    0.49
    lej
    0.49
    ni
    0.49
    Programm
    0.48
    Activations Density 0.000%

    No Known Activations