© 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. 34568
    Prev
    Next
    INDEX
    Explanations

    mathematical variable names

    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
     geometrical
    0.44
     apex
    0.42
     corner
    0.41
    вами
    0.39
    ៃ
    0.38
     уг
    0.38
     infinites
    0.38
    Spiral
    0.38
     visualise
    0.38
     yarat
    0.37
    POSITIVE LOGITS
    セ
    0.42
     السابق
    0.40
    áo
    0.39
     Gutierrez
    0.39
    答应
    0.39
     रुद्र
    0.39
     inclement
    0.38
     M
    0.38
     Tzu
    0.38
    ȟ
    0.38
    Activations Density 0.001%

    No Known Activations