© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1070
    Prev
    Next
    INDEX
    Explanations

    expressing thought or opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entend
    1.64
    ভাবে
    1.51
     chercher
    1.48
     retour
    1.48
    cular
    1.41
    صة
    1.38
    Ռ
    1.38
    ات
    1.37
    ность
    1.36
     beachten
    1.34
    POSITIVE LOGITS
    ရှား
    2.43
    ส์
    2.08
    办法
    2.07
    andfeel
    1.96
     fondly
    1.92
     ملي
    1.88
     morphogenesis
    1.88
    n
    1.87
    cadilly
    1.86
    ﻖ
    1.86
    Activations Density 0.100%

    No Known Activations