© 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. 182510
    Prev
    Next
    INDEX
    Explanations

    allow limitations

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

    scientific perspective

    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
    機器
    0.54
     კონ
    0.48
    痠
    0.48
    食べ
    0.47
    料理
    0.46
     მნიშვნელ
    0.46
    最
    0.45
     maß
    0.45
    ých
    0.45
    測定
    0.44
    POSITIVE LOGITS
    :
    0.47
     सरफेस
    0.47
    Lovely
    0.46
     searching
    0.44
    Everybody
    0.44
    数据显示
    0.41
    ९
    0.41
     dic
    0.41
     Piccadilly
    0.40
     Cambrian
    0.40
    Activations Density 0.001%

    No Known Activations