© 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. 64000
    Prev
    Next
    INDEX
    Explanations

    human characteristics and abstract 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_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
     चाँ
    0.45
     gelatin
    0.45
     compds
    0.45
     Sulf
    0.44
     veloce
    0.43
    軟件
    0.43
     sulf
    0.43
    喿
    0.42
     சுத்த
    0.42
     빠른
    0.42
    POSITIVE LOGITS
    Endpoint
    0.46
    newMessage
    0.44
    Context
    0.44
     comunicado
    0.43
     epistle
    0.42
    otification
    0.41
    wp
    0.40
    RequestContext
    0.40
    Connections
    0.40
     communiqué
    0.40
    Activations Density 0.016%

    No Known Activations