© 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. 50098
    Prev
    Next
    INDEX
    Explanations

    action commands

    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
    Infinite
    0.39
    វេល
    0.38
     सच्ची
    0.38
     infinite
    0.38
     تعالى
    0.37
     ```
    0.37
     تخلی
    0.37
    無限
    0.37
    และความ
    0.37
     evita
    0.37
    POSITIVE LOGITS
    »
    0.44
     আমার
    0.43
    !»
    0.41
     +"
    0.38
    」
    0.38
     my
    0.38
     ഇപ്പോ
    0.38
     anyway
    0.37
     dieses
    0.37
     ></
    0.37
    Activations Density 0.030%

    No Known Activations