© 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. 1363
    Prev
    Next
    INDEX
    Explanations

    protein binding sites

    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
     ezingu
    0.58
    arranty
    0.56
    㓶
    0.55
    ্যন্তরীণ
    0.54
    OURCES
    0.53
     invoicing
    0.53
    ាតុ
    0.53
    usingCamera
    0.53
    <unused202>
    0.52
     répartition
    0.51
    POSITIVE LOGITS
     Proteins
    1.10
     proteins
    1.06
     protein
    1.04
     Protein
    0.98
     molecules
    0.93
     binding
    0.92
    Protein
    0.90
     conformational
    0.89
     molecule
    0.88
     Molecular
    0.88
    Activations Density 0.061%

    No Known Activations