© 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. 41120
    Prev
    Next
    INDEX
    Explanations

    expressing concession

    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
    НУ
    -1.45
     in
    -1.39
     just
    -1.36
    ⸫
    -1.36
    Ἢ
    -1.26
    bakter
    -1.24
    ᴉ
    -1.23
     of
    -1.20
     れ
    -1.20
     isn
    -1.17
    POSITIVE LOGITS
    喽
    1.36
    覚悟
    1.22
     yawn
    1.19
     moan
    1.16
     Даже
    1.15
     refactor
    1.14
     Pentru
    1.13
     kosz
    1.13
    明显的
    1.13
     réglable
    1.12
    Activations Density 0.026%

    No Known Activations