© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1939
    Prev
    Next
    INDEX
    Explanations

    numbers and patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    യിലെ
    0.65
     resultante
    0.64
     được
    0.63
     című
    0.63
     situado
    0.61
     сможет
    0.61
    లోని
    0.61
    鋈
    0.61
     முடிந்த
    0.61
     môn
    0.61
    POSITIVE LOGITS
     deleting
    0.63
     one
    0.62
     number
    0.60
     harmful
    0.60
     negative
    0.59
    数
    0.58
     zero
    0.58
     deletion
    0.57
     repair
    0.57
     deleted
    0.56
    Activations Density 0.450%

    No Known Activations