© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 215388
    Prev
    Next
    INDEX
    Explanations

    cell and column references

    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
    Negative Logits
    蛞
    0.43
     সমন্ব
    0.43
    ught
    0.42
     тща
    0.42
     গ্যাসের
    0.42
    <unused1911>
    0.42
     granola
    0.41
    軲
    0.41
     precisar
    0.41
    udrait
    0.41
    POSITIVE LOGITS
     AA
    0.46
     AB
    0.44
     ID
    0.42
     AAA
    0.41
     AL
    0.41
     ABI
    0.41
     grid
    0.41
    IN
    0.40
     ]
    0.39
     B
    0.39
    Activations Density 0.012%

    No Known Activations