© 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
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 558
    Prev
    Next
    INDEX
    Explanations

    language and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    らう
    1.66
     arrived
    1.63
    ijl
    1.62
    戳
    1.60
     members
    1.58
     won
    1.54
    tained
    1.54
     arrive
    1.54
    大事
    1.51
    iteiten
    1.50
    POSITIVE LOGITS
    测试
    2.54
    NING
    2.54
     superoxide
    2.38
    试验
    2.34
    TEST
    2.27
    OnUiThread
    2.24
     autonome
    2.21
    𝘯
    2.14
     commerciali
    2.12
     테스트
    2.12
    Activations Density 0.051%

    No Known Activations