© 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. 11443
    Prev
    Next
    INDEX
    Explanations

    address parts

    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
    <unused540>
    1.01
    <unused483>
    0.99
    <unused660>
    0.98
    iex
    0.97
    <unused2027>
    0.96
    <unused2100>
    0.96
    Replacement
    0.96
     substitutional
    0.96
    捩
    0.96
    ूटूथ
    0.96
    POSITIVE LOGITS
     high
    0.89
     steel
    0.75
     dust
    0.74
     hard
    0.74
     clean
    0.73
     after
    0.71
     water
    0.70
     High
    0.69
    ↵
    0.68
     perfect
    0.68
    Activations Density 0.090%

    No Known Activations