© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3112
    Prev
    Next
    INDEX
    Explanations

    1 followed by a separator or range

    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
     trece
    0.89
    ฯ
    0.88
     pés
    0.85
    ా
    0.81
     conter
    0.80
     съ
    0.79
     împ
    0.77
     altro
    0.77
     pux
    0.76
     calcule
    0.75
    POSITIVE LOGITS
    ️⃣
    1.27
    \!\
    1.12
    ⃣
    1.10
    Catalogue
    0.96
    특별시
    0.95
    setAttribute
    0.84
    ChildScrollView
    0.83
    publish
    0.83
    Attribute
    0.83
    었다
    0.82
    Activations Density 0.169%

    No Known Activations