© 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-262K
    7. 215640
    Prev
    Next
    INDEX
    Explanations

    small sayings or paper fortunes

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     the
    0.58
     a
    0.48
     is
    0.46
     some
    0.46
     firmly
    0.46
     দ্য
    0.45
     just
    0.45
     ông
    0.44
     this
    0.42
    ট্রোল
    0.42
    POSITIVE LOGITS
     motto
    0.47
     ಕೆಲಸ
    0.46
    }(-\
    0.44
     vence
    0.44
     olmayan
    0.44
     workmanship
    0.43
     commotion
    0.42
    ንም
    0.41
     litmus
    0.41
     loophole
    0.40
    Activations Density 0.002%

    No Known Activations