© 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. 198125
    Prev
    Next
    INDEX
    Explanations

    German Contemporary Literature

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

    defining words and concepts

    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
    টি
    0.57
    顯
    0.55
    显
    0.48
    ０
    0.48
    􀂃
    0.48
    чной
    0.47
    辗
    0.47
    綃
    0.47
    чно
    0.47
    тип
    0.47
    POSITIVE LOGITS
    ဆေး
    0.52
    şi
    0.46
     pérd
    0.46
    il
    0.45
    man
    0.45
     légumes
    0.45
     différents
    0.45
    Württemberg
    0.45
    ilí
    0.45
    z
    0.44
    Activations Density 0.001%

    No Known Activations