© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72746
    Prev
    Next
    INDEX
    Explanations

    acronyms starting with i

    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
    Of
    -3.16
    C
    -2.72
    D
    -2.39
    E
    -2.34
    and
    -2.33
    R
    -2.33
    A
    -2.31
    L
    -2.27
    0
    -2.27
    ci
    -2.25
    POSITIVE LOGITS
     Then
    2.47
    偲
    2.25
     tuss
    2.19
    翃
    2.14
     装置
    2.14
    翾
    2.09
    .
    2.06
    🕗
    2.00
     it
    1.99
    ଽ
    1.97
    Activations Density 0.696%

    No Known Activations