© 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. 534
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
     another
    1.13
     आणखी
    0.91
     some
    0.89
     other
    0.89
     Another
    0.87
     autre
    0.85
     또
    0.83
     slight
    0.83
    another
    0.81
     juist
    0.80
    POSITIVE LOGITS
    1
    1.47
    Section
    1.35
    ১
    1.35
     ১
    1.35
    ۱
    1.32
    １
    1.31
     ۱
    1.26
    First
    1.26
    Primero
    1.25
    Step
    1.24
    Activations Density 3.487%

    No Known Activations