Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47143
    Prev
    Next
    INDEX
    Explanations

    consent of

    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_65k_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
     duur
    1.02
     оста
    1.00
     memungkinkan
    0.95
    Ј
    0.94
    Haryana
    0.93
    ту
    0.90
     penyebab
    0.89
     forment
    0.89
     Ис
    0.88
     repos
    0.88
    POSITIVE LOGITS
    ن
    1.19
    न
    1.06
    oğlu
    1.03
    tedir
    1.01
    အစား
    1.00
    气质
    1.00
    ﻦ
    1.00
    ptides
    0.98
    pseudo
    0.98
    lı
    0.97
    Activations Density 0.000%

    No Known Activations