© 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. 4713
    Prev
    Next
    INDEX
    Explanations

    taxonomy and species classification

    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
    ナソニック
    0.68
    ্যাশ
    0.68
    យៈ
    0.63
    ッサージ
    0.61
    コーチ
    0.61
    ックレス
    0.61
    ួក
    0.60
    🥯
    0.58
    ปลี่ยน
    0.57
     magnetically
    0.57
    POSITIVE LOGITS
     taxonomic
    1.57
     Taxonomic
    1.54
     Biodiversity
    1.41
     taxonom
    1.37
     Taxonomy
    1.36
     Species
    1.32
     taxon
    1.31
     taxonomy
    1.27
     biodiversity
    1.26
     species
    1.23
    Activations Density 0.009%

    No Known Activations