© 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. 68187
    Prev
    Next
    INDEX
    Explanations

    income statistics and country comparisons

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

    not trained with GPT

    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
    Not in Any Lists

    No Comments

    Negative Logits
     право
    0.44
     বর্ণ
    0.44
    鹖
    0.43
    ዐይን
    0.42
    ☀
    0.41
     அழகு
    0.40
    ፊ
    0.39
    未来
    0.39
    スコ
    0.39
    電力
    0.39
    POSITIVE LOGITS
     FTIR
    0.48
     Ryzen
    0.47
     MSRP
    0.47
     manufacturer
    0.46
     Medicare
    0.44
     IgG
    0.44
    ры
    0.43
     OEMs
    0.43
    ravy
    0.43
     Syed
    0.42
    Activations Density 0.002%

    No Known Activations