© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246722
    Prev
    Next
    INDEX
    Explanations

    single select options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    માં
    0.45
     engineer
    0.44
     thym
    0.44
     exigir
    0.44
    रो
    0.44
     }]
    0.43
     Engineer
    0.43
     hei
    0.43
     विफल
    0.42
     engineers
    0.41
    POSITIVE LOGITS
    쥬
    0.51
     deň
    0.49
    쑹
    0.43
    そこ
    0.43
     CQG
    0.43
    reasonable
    0.42
    흩
    0.42
    淳
    0.42
    紘
    0.42
     circunfer
    0.41
    Activations Density 0.000%

    No Known Activations