© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12925
    Prev
    Next
    INDEX
    Explanations

    number of necessity or estimation

    np_acts-logits-general · gemini-2.5-flash-lite

    calculate division approximate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    when
    0.47
    t
    0.43
    CS
    0.42
    to
    0.40
    ut
    0.38
     when
    0.37
    car
    0.36
    d
    0.36
    so
    0.36
    md
    0.36
    POSITIVE LOGITS
     इंट्रो
    0.48
     coarser
    0.48
    粗
    0.47
     मोटी
    0.46
     মোটা
    0.45
     épaisse
    0.44
     esboço
    0.43
     afuera
    0.42
     அழுத்த
    0.42
     আনু
    0.41
    Activations Density 0.001%

    No Known Activations