© 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. 14547
    Prev
    Next
    INDEX
    Explanations

    pure elemental descriptors

    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
    世界杯
    2.83
    𝐬
    2.79
     為
    2.77
     BUG
    2.75
     Mb
    2.74
     quake
    2.73
    સ
    2.72
     MBE
    2.71
    subequations
    2.71
     encabez
    2.67
    POSITIVE LOGITS
    粹
    2.52
    粋
    2.34
    i
    2.30
    پلز
    2.26
    도로
    2.26
    νε
    2.25
    zed
    2.08
    ető
    2.05
    ेश्वर
    2.01
    pä
    2.00
    Activations Density 0.013%

    No Known Activations