© 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-262K
    7. 36054
    Prev
    Next
    INDEX
    Explanations

    API endpoints and templates

    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_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
     ऑर्गेनिक
    0.38
     মাননীয়
    0.37
     cyl
    0.37
     hervor
    0.37
     massima
    0.37
    霁
    0.37
     glyph
    0.37
    礬
    0.36
    otype
    0.36
    hede
    0.35
    POSITIVE LOGITS
     $\{
    1.45
     '{
    1.23
     $\{\
    1.22
     \{
    1.21
     "{
    1.20
    $\{
    1.13
    \{
    1.13
    ("{
    1.10
     `{
    1.05
    "{
    1.04
    Activations Density 0.009%

    No Known Activations