© 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. 69738
    Prev
    Next
    INDEX
    Explanations

    scale from

    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
     проє
    1.71
    滨
    1.60
     estratégica
    1.56
    eseorang
    1.55
    бол
    1.53
    консу
    1.50
    etzte
    1.49
    вари
    1.48
    ibuya
    1.47
     Шрифт
    1.46
    POSITIVE LOGITS
     G
    1.52
     money
    1.35
     K
    1.34
    G
    1.32
     words
    1.29
     best
    1.28
    Fancy
    1.28
    from
    1.26
     S
    1.24
    スケジュール
    1.23
    Activations Density 0.013%

    No Known Activations