© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8442
    Prev
    Next
    INDEX
    Explanations

    SQL FROM clause

    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_22_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
    ↵
    1.22
    </h1>
    0.92
     kang
    0.83
     Gesetz
    0.82
     IP
    0.81
     IL
    0.81
     comentado
    0.79
    تميز
    0.78
    TintMode
    0.78
    Passwords
    0.78
    POSITIVE LOGITS
    anguages
    0.90
    omorphic
    0.83
    \}$.
    0.82
     \}
    0.80
    \}.
    0.80
    -]
    0.80
    ορ
    0.79
    mainan
    0.79
    havi
    0.79
    ]。
    0.78
    Activations Density 0.066%

    No Known Activations