© 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. 41-GEMMASCOPE-2-RES-262K
    7. 31936
    Prev
    Next
    INDEX
    Explanations

    hydrogen flame

    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_all/layer_41_width_262k_l0_big
    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
     tessel
    0.43
     mosaics
    0.43
     waistcoat
    0.43
    ಘ
    0.42
     polysaccharides
    0.42
    grab
    0.42
     exploded
    0.41
     நிறுவனம்
    0.40
     porous
    0.40
     dumbbells
    0.40
    POSITIVE LOGITS
     blades
    1.31
     blade
    1.29
     Blades
    1.13
    blade
    1.09
    Blade
    1.09
     Blade
    1.05
     flame
    1.05
     flames
    0.97
    刃
    0.96
     Flames
    0.84
    Activations Density 0.006%

    No Known Activations