© 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. 14497
    Prev
    Next
    INDEX
    Explanations

    url components or paths

    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
    此之外
    3.07
    IRCONIUM
    3.01
    Qualified
    2.95
    s
    2.91
    tls
    2.90
    嗒
    2.90
     EnglishChoose
    2.86
     RenderTexture
    2.83
    grace
    2.81
    ித்த
    2.78
    POSITIVE LOGITS
     miras
    2.30
    M
    2.20
    ó
    2.15
    rá
    2.10
    াক
    2.09
    dec
    2.05
    ق
    2.02
    ker
    1.98
    ளாக்
    1.97
    ደር
    1.97
    Activations Density 0.006%

    No Known Activations