© 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. 116077
    Prev
    Next
    INDEX
    Explanations

    long-term stays

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

    cornerstone revenue

    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
     Ү
    0.64
     кине
    0.55
     सेंटीमीटर
    0.49
     சிரி
    0.48
     великолеп
    0.47
     दमदार
    0.47
     मिनिट
    0.47
     जॉ
    0.47
     ил
    0.47
     होगा
    0.46
    POSITIVE LOGITS
    制度
    0.49
    As
    0.48
    鍰
    0.47
    l
    0.47
    真實
    0.46
    Employer
    0.46
     grada
    0.46
     paio
    0.45
    遗
    0.45
    Known
    0.45
    Activations Density 0.000%

    No Known Activations