© 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. 11524
    Prev
    Next
    INDEX
    Explanations

    Andy Weir sci-fi

    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
    🗨
    3.01
     忄
    2.98
    vvvert
    2.95
    <unused117>
    2.94
    
    2.92
    䥑
    2.86
    𒂊
    2.85
    lbrakk
    2.83
     womenProduct
    2.82
    푅
    2.82
    POSITIVE LOGITS
    2
    2.48
    3
    2.41
    1
    2.17
    nya
    2.09
    4
    2.09
    line
    2.04
    6
    1.94
    shot
    1.83
    sz
    1.79
    5
    1.78
    Activations Density 0.004%

    No Known Activations