© 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. 31575
    Prev
    Next
    INDEX
    Explanations

    but... still

    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
     दाख
    0.43
     fortunately
    0.43
     \{
    0.43
     Fortunately
    0.42
     আবদ্ধ
    0.42
     спокойно
    0.41
     \{\
    0.40
     thankfully
    0.40
    㜖
    0.40
     Thankfully
    0.40
    POSITIVE LOGITS
     still
    0.58
     inevitably
    0.55
    still
    0.53
     inevitable
    0.50
    Still
    0.46
     STILL
    0.45
     unavoid
    0.45
     unavoidable
    0.44
     tempted
    0.43
     Still
    0.41
    Activations Density 0.170%

    No Known Activations