© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109099
    Prev
    Next
    INDEX
    Explanations

    Meteorology and named individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    };
    -0.77
    Usually
    -0.71
    rogly
    -0.70
    瘟
    -0.70
     Usually
    -0.70
    時間の
    -0.69
    };
    -0.69
     time
    -0.68
     usually
    -0.68
    וֹת
    -0.67
    POSITIVE LOGITS
     climat
    1.08
     Climat
    0.94
     Wea
    0.87
     Diab
    0.86
     Roch
    0.83
     balances
    0.80
    forcing
    0.80
    𝔟
    0.80
    IFIC
    0.80
     якого
    0.79
    Activations Density 0.004%

    No Known Activations