© 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. 14326
    Prev
    Next
    INDEX
    Explanations

    multiple languages and domains

    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
    ឿ
    3.08
    ዦ
    2.87
    ंपल
    2.81
    <{},
    2.80
    SHIP
    2.79
    ន៍
    2.77
    anganese
    2.74
     fadeInLeft
    2.74
     CONTRIBUTORS
    2.73
    neutrophiles
    2.73
    POSITIVE LOGITS
    ه
    3.36
    es
    2.98
    er
    2.89
    い
    2.86
    i
    2.60
    u
    2.51
    ed
    2.47
    ing
    2.24
    ه‌ای
    2.22
    도
    2.18
    Activations Density 0.002%

    No Known Activations