© 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-65K
    7. 4428
    Prev
    Next
    INDEX
    Explanations

    NVIDIA RTX GPUs

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    \}$.
    0.46
    atorial
    0.41
    \}$,
    0.37
     antiqu
    0.37
     вну
    0.36
    \}.
    0.36
    ament
    0.36
     ਵਾਲ
    0.35
    ț
    0.35
     dominion
    0.35
    POSITIVE LOGITS
     RT
    0.61
     rt
    0.60
     RTI
    0.59
    RT
    0.59
     RTS
    0.59
     Rt
    0.55
     RTP
    0.52
    RTC
    0.51
    Rt
    0.50
     RTX
    0.50
    Activations Density 0.037%

    No Known Activations