© 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. 9-GEMMASCOPE-2-RES-16K
    7. 4
    Prev
    Next
    INDEX
    Explanations

    instructions, questions, and information

    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_9_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
     Additionally
    0.66
    Additionally
    0.60
    primarily
    0.59
     significantly
    0.59
    ¹.
    0.59
     sustainably
    0.59
     Είναι
    0.57
    📈
    0.57
     underpinned
    0.56
     Furthermore
    0.55
    POSITIVE LOGITS
     honom
    0.41
    ɳ
    0.41
     bertanya
    0.40
    mathrm
    0.40
    png
    0.39
    whis
    0.39
    ][-
    0.39
    ๆ
    0.38
    ಾತ
    0.38
    toy
    0.37
    Activations Density 3.683%

    No Known Activations