© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11520
    Prev
    Next
    INDEX
    Explanations

    typedef struct {

    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_16k_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
     يحدث
    0.41
     implies
    0.39
     establishes
    0.39
     recovers
    0.38
     prescribes
    0.38
     প্রেস
    0.38
     (`
    0.37
     agrees
    0.37
     Gives
    0.37
     ছাড়া
    0.37
    POSITIVE LOGITS
     {
    0.53
    {
    0.51
     interstitiis
    0.45
    ecimento
    0.43
    angkutan
    0.40
    igungs
    0.39
    isn
    0.38
     ök
    0.38
     Helic
    0.38
     {-
    0.38
    Activations Density 0.050%

    No Known Activations