© 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. 21624
    Prev
    Next
    INDEX
    Explanations

    AI research, ECG, sets, channels

    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
     phenytoin
    0.43
     distributive
    0.40
     Usual
    0.39
     thèse
    0.39
     culmination
    0.39
     nub
    0.38
     cuad
    0.38
     =&
    0.38
     ἢ
    0.37
     लिंग
    0.37
    POSITIVE LOGITS
     الجمهور
    0.40
    rolog
    0.40
    Automatically
    0.40
    šć
    0.39
    Initialization
    0.39
    clientId
    0.39
    uddersfield
    0.38
    Attach
    0.38
     Admir
    0.38
    ឡើង
    0.37
    Activations Density 0.000%

    No Known Activations