© 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. 31-GEMMASCOPE-2-RES-262K
    7. 75062
    Prev
    Next
    INDEX
    Explanations

    address public, padlock icon

    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
    BinaryOperation
    0.44
    Appendix
    0.43
    ╁
    0.42
    WebpackPlugin
    0.41
     đạt
    0.40
     ہوگا
    0.40
     येईल
    0.40
    osperm
    0.40
    出会
    0.40
    ܙ
    0.39
    POSITIVE LOGITS
     crush
    0.52
     abused
    0.52
     bowed
    0.52
     requested
    0.51
    NOT
    0.51
     not
    0.50
     recent
    0.50
     cared
    0.50
    ні
    0.50
    На
    0.49
    Activations Density 0.005%

    No Known Activations