© 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-65K
    7. 31533
    Prev
    Next
    INDEX
    Explanations

    programming variable names

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     assh
    0.45
    ™.
    0.41
     اللَّ
    0.40
    ↵
    0.38
     Tennyson
    0.38
    🌼
    0.37
     ರಲ್ಲಿ
    0.37
    __.
    0.37
     तीव्रता
    0.35
     এটি
    0.34
    POSITIVE LOGITS
    )^*
    0.40
    ného
    0.40
     camping
    0.39
     by
    0.38
    ಂತಿ
    0.38
     உடைய
    0.38
     парк
    0.38
    ividades
    0.37
    가는
    0.36
    鰱
    0.35
    Activations Density 0.005%

    No Known Activations