© 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. 23351
    Prev
    Next
    INDEX
    Explanations

    eggs

    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
     अखंड
    0.43
    เฉ
    0.43
     tongs
    0.42
    仟
    0.42
    gué
    0.41
     postnatal
    0.40
    紋
    0.39
    irsty
    0.39
    𐱅
    0.39
     fathers
    0.38
    POSITIVE LOGITS
     eggs
    1.47
    卵
    1.41
     egg
    1.39
     Eggs
    1.38
    Eggs
    1.34
     Egg
    1.29
    eggs
    1.27
    Egg
    1.27
    egg
    1.20
     яй
    1.20
    Activations Density 0.006%

    No Known Activations