© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 52580
    Prev
    Next
    INDEX
    Explanations

    specific resource names

    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
     Productos
    0.41
     getline
    0.39
    තික
    0.38
     τῶν
    0.38
     આપી
    0.37
    Pada
    0.37
    댈
    0.37
    疟
    0.36
    LogLevel
    0.36
     isos
    0.36
    POSITIVE LOGITS
    ៖
    0.50
     :'
    0.45
    !:
    0.44
    ：“
    0.42
     fashioned
    0.42
     Exec
    0.40
     futuristic
    0.40
     präsentiert
    0.39
    这些
    0.39
     désormais
    0.38
    Activations Density 0.002%

    No Known Activations