© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 140
    Prev
    Next
    INDEX
    Explanations

    Someone else, anyone who

    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
    Negative Logits
     itself
    0.45
     ஆகியவற்ற
    0.42
    },
    0.42
    }
    0.42
    <0x0D>
    0.41
    そして
    0.41
    และ
    0.39
    にて
    0.39
    時に
    0.38
     /
    0.37
    POSITIVE LOGITS
     who
    0.86
    who
    0.72
     else
    0.70
     whos
    0.66
     кто
    0.59
     Who
    0.59
    Else
    0.58
     kdo
    0.58
     quién
    0.58
    谁
    0.57
    Activations Density 0.369%

    No Known Activations