© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22184
    Prev
    Next
    INDEX
    Explanations

    words starting with abstract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     The
    -2.55
     they
    -2.28
     alcune
    -2.08
     следующие
    -2.05
    ཽ
    -2.03
     alguns
    -2.00
     "
    -1.98
    ⟣
    -1.96
     creat
    -1.96
     bleak
    -1.95
    POSITIVE LOGITS
    ൎ
    3.31
    沇
    2.53
     unrelenting
    2.30
    Using
    2.28
     號
    2.25
    鋮
    2.22
     RSITY
    2.22
    After
    2.20
    晅
    2.17
    ！！”
    2.16
    Activations Density 0.013%

    No Known Activations