© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54087
    Prev
    Next
    INDEX
    Explanations

    money and time durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝚆
    0.43
    Description
    0.42
    Definitions
    0.41
    Ac
    0.39
     মুসলমানদের
    0.39
    ല്ലോ
    0.38
     بالأ
    0.38
     Parab
    0.38
    萩
    0.38
     Histories
    0.38
    POSITIVE LOGITS
     tuned
    0.44
    UserRootDir
    0.39
    tuned
    0.37
     konuştu
    0.37
     tune
    0.37
    ̀nh
    0.36
     قه
    0.36
     aired
    0.35
     Tune
    0.35
    пей
    0.34
    Activations Density 0.000%

    No Known Activations