© 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. 11849
    Prev
    Next
    INDEX
    Explanations

    such content or information

    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
    𝗧
    0.60
     ntawm
    0.57
    𝟯
    0.57
    ла
    0.56
     それぞれ
    0.56
     gonorrhea
    0.55
    𝗠
    0.55
     всі
    0.55
     सबै
    0.54
     beforeEach
    0.54
    POSITIVE LOGITS
    is
    0.84
     an
    0.80
    t
    0.79
    c
    0.74
    ut
    0.73
    such
    0.71
    er
    0.64
    ot
    0.64
    p
    0.63
    v
    0.63
    Activations Density 0.167%

    No Known Activations