© 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. 31-GEMMASCOPE-2-RES-262K
    7. 74566
    Prev
    Next
    INDEX
    Explanations

    not just, but rather

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     přij
    0.51
     сни
    0.49
     మర
    0.49
     принимать
    0.49
     ኩ
    0.49
     buildFor
    0.48
     同じ
    0.48
     সন্ধ
    0.48
     ברי
    0.48
     говорил
    0.47
    POSITIVE LOGITS
    sent
    0.46
    lil
    0.45
    ag
    0.45
    </code>
    0.45
     gobiernos
    0.44
    </span>
    0.44
    rose
    0.44
    いです
    0.44
     ascends
    0.44
     taxpayer
    0.43
    Activations Density 0.003%

    No Known Activations