© 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-262K
    7. 19335
    Prev
    Next
    INDEX
    Explanations

    economic impact and inflation

    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_262k_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
     문화
    0.41
    盐
    0.41
    문화
    0.40
     درباره
    0.39
    ابی
    0.39
    볼
    0.39
     सभ
    0.38
     Lv
    0.38
     দেবযানীর
    0.38
     BV
    0.38
    POSITIVE LOGITS
     creep
    0.42
     locom
    0.42
     curfew
    0.41
    lok
    0.41
     terribly
    0.41
    hid
    0.40
     pien
    0.39
     sp
    0.39
     medication
    0.39
     oxygen
    0.38
    Activations Density 0.005%

    No Known Activations