© 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. 47569
    Prev
    Next
    INDEX
    Explanations

    simple die roll

    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
     falls
    0.39
    }));
    0.39
     superconduct
    0.38
    ਾਰ
    0.38
     al
    0.37
    Dsp
    0.37
     onc
    0.36
    })}{\
    0.36
     subl
    0.36
     fall
    0.35
    POSITIVE LOGITS
     التلاميذ
    0.48
     تلاميذ
    0.48
     Schüler
    0.47
     Pupils
    0.46
    getChild
    0.42
     Birthday
    0.41
     टेट
    0.41
     hadiah
    0.41
    stituted
    0.41
    礼物
    0.41
    Activations Density 0.000%

    No Known Activations