© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14568
    Prev
    Next
    INDEX
    Explanations

    #Your [topic] [hashtag]

    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_7_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
    𝒍
    2.41
    liga
    2.27
    𝒖
    2.20
    ي
    2.15
    l
    2.15
    이라
    2.11
    y
    2.06
     tel
    1.94
     dul
    1.90
    িণী
    1.89
    POSITIVE LOGITS
    ᴇ
    2.86
    $^{
    2.72
    ᴀ
    2.59
    ᴛ
    2.48
    KURZBESCHREIBUNG
    2.47
    кло
    2.44
    ᑎ
    2.38
    ography
    2.34
    顱
    2.34
    ften
    2.30
    Activations Density 0.022%

    No Known Activations