© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10127
    Prev
    Next
    INDEX
    Explanations

    used, replaced, or transformed

    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_22_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
    Definitely
    0.79
    Previously
    0.71
    ທີ່
    0.70
    把
    0.69
     nurture
    0.69
     Definitely
    0.68
    可
    0.66
    刚
    0.66
    ர்களையும்
    0.64
     ಈಗ
    0.64
    POSITIVE LOGITS
     used
    1.33
     replaced
    1.30
     shown
    1.26
     examined
    1.21
     subjected
    1.19
     sued
    1.12
     turned
    1.12
     digunakan
    1.11
    replaced
    1.07
     applied
    1.07
    Activations Density 0.102%

    No Known Activations