© 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. 11954
    Prev
    Next
    INDEX
    Explanations

    years in, automatically negative, closest to

    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
     respeito
    0.42
    այր
    0.41
    ਧ
    0.41
     conqu
    0.40
    ester
    0.39
     ish
    0.39
    蓉
    0.39
    اه
    0.38
    руп
    0.38
     توا
    0.38
    POSITIVE LOGITS
     Solar
    0.48
     കേന്ദ്ര
    0.47
     Oracle
    0.46
     Pineapple
    0.46
     तलैया
    0.45
     действу
    0.44
     Genel
    0.44
     Michaelmas
    0.44
    ">{{
    0.43
     Gardening
    0.43
    Activations Density 0.035%

    No Known Activations