© 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-16K
    7. 2520
    Prev
    Next
    INDEX
    Explanations

    universality and totality

    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
    \
    0.48
    (
    0.44
     implied
    0.42
    0.42
     el
    0.42
     prevalent
    0.42
    já
    0.41
     on
    0.41
    concurrent
    0.40
    à
    0.40
    POSITIVE LOGITS
    这一切
    0.61
     đều
    0.54
     имеют
    0.52
     প্রতিটি
    0.52
     должны
    0.52
    人都
    0.51
     அனைத்தும்
    0.51
     बहुतेक
    0.51
     semuanya
    0.50
    ွဲ
    0.49
    Activations Density 0.127%

    No Known Activations