© 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. 74564
    Prev
    Next
    INDEX
    Explanations

    subjects introducing phrases

    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
    <unused2103>
    0.45
    कोरोना
    0.43
    țion
    0.42
    ഒരു
    0.40
    <unused721>
    0.40
     จำนวน
    0.38
    Რ
    0.38
    <unused718>
    0.38
     प्रसिद्ध
    0.37
    <unused557>
    0.37
    POSITIVE LOGITS
     monadic
    0.40
     AdS
    0.38
     antisense
    0.38
     monotonic
    0.37
     isoform
    0.37
     inset
    0.37
     adjoint
    0.37
     miR
    0.36
     ms
    0.36
     lensing
    0.36
    Activations Density 0.043%

    No Known Activations