© 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. 129616
    Prev
    Next
    INDEX
    Explanations

    like this

    np_acts-logits-general · gemini-2.5-flash-lite

    finding connections

    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
     желу
    0.56
     سک
    0.54
    ikken
    0.53
     vutto
    0.52
    GEBURTS
    0.52
    隐含规则
    0.52
     حلق
    0.51
    터
    0.49
     چار
    0.49
     زن
    0.49
    POSITIVE LOGITS
     offices
    0.48
     Offices
    0.47
     albo
    0.45
    র্ন
    0.45
     at
    0.43
    planatory
    0.43
     discovers
    0.42
    ですね
    0.41
     Halls
    0.41
     predictably
    0.41
    Activations Density 0.000%

    No Known Activations