© 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-262K
    7. 127725
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to transactions or agreements

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

    urgency and seriousness

    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_262k_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
    bmatrix
    0.46
     posee
    0.41
     ponieważ
    0.40
     posiada
    0.40
     bruge
    0.40
    \|,
    0.40
     Despite
    0.39
     namun
    0.39
     "",
    0.39
     ".",
    0.39
    POSITIVE LOGITS
    盉
    0.46
     си
    0.46
     последний
    0.46
    的時間
    0.45
     دوبارہ
    0.44
     السّ
    0.43
     د
    0.43
    时间和
    0.43
    को
    0.42
     회사
    0.42
    Activations Density 0.001%

    No Known Activations