© 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. 59590
    Prev
    Next
    INDEX
    Explanations

    liquid from eyes

    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
     mood
    0.42
     Mood
    0.38
    hedgehog
    0.38
     বন্দর
    0.38
     moods
    0.38
    Rash
    0.38
    橘
    0.38
    茷
    0.38
     Vak
    0.37
    Mood
    0.37
    POSITIVE LOGITS
     tears
    2.48
     Tears
    2.19
    涙
    2.08
     tear
    2.02
     lágrimas
    1.88
    泪
    1.85
    淚
    1.75
     Tear
    1.70
    tear
    1.65
     teard
    1.56
    Activations Density 0.004%

    No Known Activations