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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 965
    Prev
    Next
    INDEX
    Explanations

    angle bracket placeholders

    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_17_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
    ()]
    0.90
    colorful
    0.89
     McCullough
    0.89
    囯
    0.85
    ozo
    0.84
    %]
    0.83
    ]_
    0.82
    〗
    0.82
    diyl
    0.82
     Solaris
    0.81
    POSITIVE LOGITS
     <
    2.32
    <
    2.18
     <!--<
    1.87
     (<
    1.66
    -<
    1.63
    <div>
    1.60
    ><
    1.54
     '<
    1.51
    .<
    1.51
     "<
    1.50
    Activations Density 0.226%

    No Known Activations