© 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. 15-GEMMASCOPE-2-RES-262K
    7. 69897
    Prev
    Next
    INDEX
    Explanations

    care about or believe in

    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_15_width_262k_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
     have
    1.47
    詫
    1.43
     enjoy
    1.32
     quitt
    1.32
     voluntarily
    1.28
     willingly
    1.28
     hav
    1.26
     seem
    1.24
    嬿
    1.22
     belong
    1.19
    POSITIVE LOGITS
    ordum
    1.43
    不利
    1.34
    against
    1.30
    粼
    1.28
    譙
    1.27
     كويس
    1.24
    celer
    1.24
    错误的
    1.22
     kullanarak
    1.22
    liced
    1.22
    Activations Density 0.004%

    No Known Activations