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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14550
    Prev
    Next
    INDEX
    Explanations

    a poetic phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     conclusive
    1.84
    ﻲ
    1.84
    琹
    1.83
     intermin
    1.79
     ContentView
    1.78
    ﺔ
    1.75
    робнее
    1.71
     frivolous
    1.70
    ARAJYA
    1.69
     cri
    1.69
    POSITIVE LOGITS
    ň
    1.67
    ğı
    1.58
    इकिल
    1.51
     গেছেন
    1.49
    ´
    1.49
     trägt
    1.48
    blichen
    1.46
    gl
    1.43
     memiliki
    1.43
     mempunyai
    1.41
    Activations Density 0.037%

    No Known Activations