© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101382
    Prev
    Next
    INDEX
    Explanations

    speaking names

    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
    0
    -1.48
    2
    -1.47
    .'.
    -1.35
    sepatu
    -1.34
    saya
    -1.32
     concluyó
    -1.31
    の新
    -1.26
     it
    -1.26
    使用的
    -1.23
    痛い
    -1.23
    POSITIVE LOGITS
     as
    1.55
     when
    1.53
     before
    1.53
    </td>
    1.52
     if
    1.36
    驀
    1.34
    if
    1.32
    錚
    1.32
    众多
    1.30
    wikimedia
    1.30
    Activations Density 0.009%

    No Known Activations