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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1817
    Prev
    Next
    INDEX
    Explanations

    based on data

    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
    瘩
    1.09
     Bxg
    0.99
     Cobra
    0.98
     pride
    0.97
     lad
    0.97
     finner
    0.96
     linker
    0.96
     Idol
    0.95
     ambition
    0.94
     Cert
    0.94
    POSITIVE LOGITS
     данных
    1.32
    𝘁
    1.21
     données
    1.19
    数据
    1.18
    $,
    1.17
    𝘃
    1.16
     даних
    1.12
    ᆨ
    1.12
    ভি
    1.10
    ሣ
    1.08
    Activations Density 0.064%

    No Known Activations