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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10740
    Prev
    Next
    INDEX
    Explanations

    instructions and directives

    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
     neutralize
    0.86
     potenz
    0.85
     WT
    0.76
     reduce
    0.76
     variable
    0.74
    ㎠
    0.74
    ʢ
    0.73
    etails
    0.72
     CDKN
    0.71
     syringe
    0.71
    POSITIVE LOGITS
     ഞാന്‍
    0.89
     الوقت
    0.85
    數
    0.83
    嘢
    0.82
     мысли
    0.82
    Что
    0.81
    我不
    0.81
    說
    0.80
    ِ
    0.80
    何时
    0.80
    Activations Density 0.194%

    No Known Activations