© 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-262K
    7. 99876
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
    訓
    0.48
     ou
    0.47
    籀
    0.45
     রাকাত
    0.44
    йти
    0.44
     opportunità
    0.44
    통산
    0.43
    锄
    0.43
    անի
    0.42
    માન્ય
    0.42
    POSITIVE LOGITS
    i
    0.52
    igare
    0.45
     dices
    0.45
    ==="
    0.45
    separ
    0.44
    dh
    0.44
     globules
    0.44
    da
    0.44
     버튼
    0.43
    it
    0.43
    Activations Density 0.001%

    No Known Activations