© 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. 160910
    Prev
    Next
    INDEX
    Explanations

    listing related qualifiers

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

    economic comparison and classification

    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
    将在
    0.49
    💐
    0.48
     Герма
    0.46
     partenariat
    0.46
    懿
    0.45
    语音
    0.45
    匿名
    0.45
    荣耀
    0.44
     কাজে
    0.44
    转化为
    0.44
    POSITIVE LOGITS
     besk
    0.47
     остальных
    0.47
     relativa
    0.46
     relativo
    0.45
     opis
    0.45
     および
    0.45
     )\
    0.45
    その他の
    0.44
     autres
    0.44
     region
    0.43
    Activations Density 0.002%

    No Known Activations