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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 113442
    Prev
    Next
    INDEX
    Explanations

    sets your website

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

    prevent throttling

    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
     Länder
    0.50
    нам
    0.49
     Ländern
    0.48
    უმ
    0.48
     Siem
    0.48
     lã
    0.47
    Peq
    0.47
    
    0.47
     پوچھا
    0.46
     degrad
    0.46
    POSITIVE LOGITS
    ARI
    0.46
    ك
    0.46
     當
    0.44
     学習
    0.44
    }|=
    0.44
    泷
    0.43
    ATE
    0.42
     แปล
    0.42
    Ainsi
    0.42
    アプリ
    0.42
    Activations Density 0.000%

    No Known Activations