© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15753
    Prev
    Next
    INDEX
    Explanations

    safety shield

    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_13_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
     heroic
    2.10
     Ayrıca
    2.03
     Bengali
    1.96
    <unused442>
    1.92
     orthodox
    1.92
    <unused2000>
    1.91
    <unused1827>
    1.91
     Poe
    1.91
     Hitler
    1.90
     Narayan
    1.89
    POSITIVE LOGITS
    展开
    1.01
    展開
    0.98
    5
    0.98
    7
    0.96
    invest
    0.96
     handle
    0.94
    6
    0.94
    خت
    0.94
    2
    0.92
    “
    0.90
    Activations Density 0.000%

    No Known Activations