© 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. 7903
    Prev
    Next
    INDEX
    Explanations

    Cold War

    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
    <unused2151>
    1.66
    OscInitStruct
    1.57
    ]/*
    1.51
    节点
    1.46
    <unused786>
    1.45
     presiding
    1.44
    <unused2106>
    1.44
    <unused2091>
    1.43
    <unused2121>
    1.43
    <unused890>
    1.41
    POSITIVE LOGITS
    ”
    1.13
    due
    1.09
    nya
    1.08
    mis
    1.06
     alte
    1.05
    m
    1.05
     ”
    1.04
    ly
    1.04
    must
    1.03
     Shall
    1.01
    Activations Density 0.000%

    No Known Activations