© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158064
    Prev
    Next
    INDEX
    Explanations

    adding or facilitating

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

    moral scale

    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
    ర్‌
    0.50
    ﾝ
    0.48
     Nachdem
    0.48
    
    0.47
    วรร
    0.46
     plaatsen
    0.46
     vorgesch
    0.46
    İŞ
    0.45
    楖
    0.42
     passages
    0.42
    POSITIVE LOGITS
    ati
    0.50
    粿
    0.49
    ти
    0.48
    adino
    0.48
    ariu
    0.48
    uti
    0.47
    िटीज
    0.47
    anh
    0.47
    行为
    0.47
    ौती
    0.46
    Activations Density 0.001%

    No Known Activations