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. 1984
    Prev
    Next
    INDEX
    Explanations

    we can

    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
    s
    0.72
    to
    0.65
    u
    0.58
    te
    0.57
    k
    0.57
    on
    0.57
    ﻭ
    0.56
    mente
    0.56
    t
    0.55
    و
    0.54
    POSITIVE LOGITS
    ខ្ញុំ
    0.80
     можем
    0.78
    chsler
    0.76
     pouvons
    0.75
     ourselves
    0.73
     devons
    0.72
     знаем
    0.71
     allons
    0.70
     хотим
    0.68
    Tenemos
    0.65
    Activations Density 0.729%

    No Known Activations