© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8345
    Prev
    Next
    INDEX
    Explanations

    head lamp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
      
    0.64
     ：
    0.63
    :“
    0.58
     sassy
    0.55
     grapefruit
    0.54
     …”
    0.54
     สามารถ
    0.53
     Çok
    0.53
     但是
    0.52
     मल्टी
    0.51
    POSITIVE LOGITS
     wellknown
    0.54
     socalled
    0.53
     $<$
    0.52
     себе
    0.49
     (=
    0.49
     or
    0.48
     prace
    0.48
     interpolated
    0.47
     جوجل
    0.47
     laterally
    0.46
    Activations Density 0.002%

    No Known Activations