© 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-65K
    7. 20910
    Prev
    Next
    INDEX
    Explanations

    finding lists and information

    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_65k_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
     database
    0.38
    笑道
    0.37
     жизнь
    0.36
     SQLite
    0.36
     growth
    0.36
     mortality
    0.36
     .
    0.35
     vaccination
    0.35
     Mortality
    0.35
     reopening
    0.35
    POSITIVE LOGITS
    帥
    0.44
    ján
    0.43
     remplir
    0.42
    ගෙන
    0.41
    හාර
    0.41
     પ્રે
    0.41
     перспекти
    0.40
    ibbean
    0.40
     fokus
    0.40
    anbul
    0.40
    Activations Density 0.001%

    No Known Activations