© 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. 9159
    Prev
    Next
    INDEX
    Explanations

    similes with as

    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
    சாக
    0.43
     saludable
    0.42
    اندار
    0.41
    є
    0.41
    Avec
    0.40
    єкт
    0.40
     oficialmente
    0.40
    Ya
    0.38
    จน
    0.38
    Au
    0.38
    POSITIVE LOGITS
     any
    0.54
     it
    0.45
     النار
    0.44
     he
    0.43
     श्रीकृष्ण
    0.43
     your
    0.43
     ب
    0.43
     أي
    0.42
     n
    0.42
    rators
    0.42
    Activations Density 0.047%

    No Known Activations