© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 58373
    Prev
    Next
    INDEX
    Explanations

    electrical charge

    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
    ipsis
    0.42
     meditation
    0.42
     अनुमो
    0.41
    彿
    0.40
     NAVIGATION
    0.39
    INavigation
    0.39
     Mew
    0.39
    <unused597>
    0.38
     niv
    0.38
    夹
    0.38
    POSITIVE LOGITS
     charge
    2.47
     charges
    2.41
    charge
    2.23
     Charge
    2.22
    Charge
    2.20
     Charges
    2.16
    Charges
    2.14
    charges
    2.02
    電荷
    1.91
     चार्ज
    1.86
    Activations Density 0.009%

    No Known Activations