© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1698
    Prev
    Next
    INDEX
    Explanations

    frameworks, exploitation, approaches, sexuality, dreams

    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_40_width_65k_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
     کہتے
    0.31
    だけど
    0.31
     Vielleicht
    0.30
     Maybe
    0.30
     Temos
    0.29
     بتوان
    0.29
     चाहें
    0.28
    ۔
    0.28
     বলেছিলেন
    0.27
    してた
    0.27
    POSITIVE LOGITS
     is
    0.53
     makes
    0.52
     puts
    0.51
     adds
    0.50
     constitutes
    0.50
     creates
    0.49
     goes
    0.46
     requires
    0.45
     surpasses
    0.45
     diminishes
    0.44
    Activations Density 0.480%

    No Known Activations