© 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. 8930
    Prev
    Next
    INDEX
    Explanations

    worth it

    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
     deserves
    0.96
     deserve
    0.90
    deserved
    0.71
     justifying
    0.69
     deserved
    0.64
    เติม
    0.63
     deserving
    0.62
    🆁
    0.61
     should
    0.61
     justifies
    0.60
    POSITIVE LOGITS
     divergences
    0.63
     stipulated
    0.59
     troubles
    0.57
    ों
    0.57
    的变化
    0.57
     لمع
    0.55
    ximately
    0.54
    姦
    0.54
     എല്ലാ
    0.53
    لاميذ
    0.53
    Activations Density 0.019%

    No Known Activations