© 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. 10049
    Prev
    Next
    INDEX
    Explanations

    site links and code documentation

    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
     चक्रवृद्धि
    0.73
    onesian
    0.69
     कप
    0.68
    inplace
    0.68
     मानसिक
    0.67
    yacute
    0.65
    با
    0.64
    ة
    0.63
     minValue
    0.63
    ন্দ্ব
    0.63
    POSITIVE LOGITS
     reportedly
    0.75
     publiques
    0.74
    릎
    0.73
     Brigade
    0.73
     பல்வேறு
    0.73
     oversee
    0.73
     Санкт
    0.72
     Oath
    0.72
     wren
    0.72
     diversi
    0.71
    Activations Density 0.001%

    No Known Activations