© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134110
    Prev
    Next
    INDEX
    Explanations

    specific language and description

    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_262k_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
     carvings
    0.41
     shoal
    0.41
    чему
    0.40
    灲
    0.39
    береж
    0.39
     westerly
    0.38
    坵
    0.38
    волю
    0.38
     wom
    0.37
     मर्द
    0.37
    POSITIVE LOGITS
     confidently
    0.41
     loud
    0.40
     Loud
    0.40
    Stability
    0.39
    Cups
    0.39
     simple
    0.38
     കൂട
    0.38
    Simple
    0.38
    큼
    0.36
    鵑
    0.36
    Activations Density 0.000%

    No Known Activations