© 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. 171858
    Prev
    Next
    INDEX
    Explanations

    Analysis and available

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

    VIEs and Chinese companies

    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
    ясплат
    0.48
    ︽
    0.47
     zabaw
    0.45
    FINISHED
    0.45
    ﺃ
    0.44
    Conteudos
    0.44
     enlace
    0.43
    ﺘ
    0.43
    ្នែក
    0.43
    ፨
    0.43
    POSITIVE LOGITS
    ovali
    0.51
    c
    0.50
    on
    0.49
    oval
    0.49
     Analysis
    0.49
     }.
    0.49
     },
    0.47
    分析
    0.47
    ings
    0.47
    isin
    0.47
    Activations Density 0.000%

    No Known Activations