© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10085
    Prev
    Next
    INDEX
    Explanations

    drug brands or products

    np_acts-logits-general · gemini-2.5-flash-lite

    import React, kernel, firewall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ‏
    0.50
    <0x0D>
    0.45
     ‎
    0.45
    _
    0.43
     Net
    0.43
     ]]
    0.42
     ·
    0.41
     |
    0.41
     ®
    0.41
    -
    0.41
    POSITIVE LOGITS
     conveyors
    0.49
    rrr
    0.45
     másik
    0.43
     hagas
    0.42
     množ
    0.42
    रीज
    0.42
     vedere
    0.41
     maken
    0.41
    লোড
    0.41
     simplesmente
    0.41
    Activations Density 0.158%

    No Known Activations