© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3127
    Prev
    Next
    INDEX
    Explanations

    most people or cases

    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
    𝚝
    3.01
     \]
    2.91
    судар
    2.69
    𝚊
    2.66
    𝚜
    2.62
    ҡ
    2.59
    
    2.54
    𝚛
    2.50
    ैनल
    2.44
    }}+
    2.43
    POSITIVE LOGITS
    <()>
    3.33
    場合に
    3.29
    нном
    2.85
    aaa
    2.75
    ا
    2.73
    رر
    2.71
    н
    2.66
     nemus
    2.62
    gaz
    2.62
    에
    2.59
    Activations Density 0.044%

    No Known Activations