© 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-262K
    7. 34480
    Prev
    Next
    INDEX
    Explanations

    date calculation

    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
     spared
    0.43
     Table
    0.39
     chemist
    0.39
    ]\
    0.38
     Okinawa
    0.38
     RDS
    0.38
     jed
    0.38
    рсә
    0.38
     pertes
    0.38
     RD
    0.37
    POSITIVE LOGITS
    
    0.42
    met
    0.37
    ꯕ
    0.37
     प्रिज्म
    0.37
    means
    0.36
    ⓘ
    0.36
    endar
    0.36
    tub
    0.36
    argon
    0.36
    ermi
    0.35
    Activations Density 0.000%

    No Known Activations