© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 582
    Prev
    Next
    INDEX
    Explanations

    identifying concepts and their attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мо
    0.65
     กล
    0.63
     T
    0.62
     นอกจาก
    0.60
    จ
    0.60
     molti
    0.59
     t
    0.58
     If
    0.58
     đồng
    0.58
     ก
    0.57
    POSITIVE LOGITS
    <unused1834>
    0.90
    <unused328>
    0.84
    octrl
    0.84
    stylish
    0.83
    constrained
    0.81
    <unused1626>
    0.80
    <unused1701>
    0.80
     ornamented
    0.80
    <unused1721>
    0.79
    assertions
    0.79
    Activations Density 0.355%

    No Known Activations