© 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. 9215
    Prev
    Next
    INDEX
    Explanations

    explaining functions and responses

    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
     jihad
    0.68
     townships
    0.64
     barcelona
    0.61
     epidemiology
    0.61
     immunology
    0.61
    <unused1024>
    0.60
     campeonato
    0.60
     sexuality
    0.59
     zoos
    0.59
     geos
    0.58
    POSITIVE LOGITS
     H
    0.85
     F
    0.81
    S
    0.79
     R
    0.78
     M
    0.75
     P
    0.75
     D
    0.74
     L
    0.74
     Re
    0.74
     S
    0.73
    Activations Density 2.330%

    No Known Activations