© 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. 31-GEMMASCOPE-2-RES-262K
    7. 43886
    Prev
    Next
    INDEX
    Explanations

    sports terminology

    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/layer_31_width_262k_l0_medium
    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
    ѕ
    0.57
    鉆
    0.47
    Ĭ
    0.43
     ਸਿੰ
    0.41
    密封
    0.41
    ଢ
    0.41
    मूलन
    0.41
     एडवा
    0.40
    Tienes
    0.40
     домаћин
    0.40
    POSITIVE LOGITS
     at
    0.51
     Jugend
    0.46
     Markt
    0.46
     hangout
    0.44
     Edit
    0.44
     about
    0.44
     Pablo
    0.43
     Edited
    0.43
     p
    0.43
     New
    0.42
    Activations Density 0.014%

    No Known Activations