© 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. 31-GEMMASCOPE-2-RES-65K
    7. 15978
    Prev
    Next
    INDEX
    Explanations

    quantities measured in cups

    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
     MERCHANTABILITY
    0.27
     рекоменду
    0.26
     Medicine
    0.26
     binoculars
    0.26
     bipolar
    0.25
     ຫຼື
    0.25
    ;,
    0.25
    的数量
    0.25
     Bagg
    0.25
    こちらの
    0.24
    POSITIVE LOGITS
    re
    0.32
    kosten
    0.31
     året
    0.30
    shel
    0.30
    set
    0.29
    tions
    0.29
    d
    0.29
    tahun
    0.29
    k
    0.29
    ์
    0.29
    Activations Density 0.033%

    No Known Activations