© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2581
    Prev
    Next
    INDEX
    Explanations

    .org/ and .com/

    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
     and
    2.03
    .
    2.00
     are
    1.89
     in
    1.87
     all
    1.81
     of
    1.80
    ,
    1.78
     have
    1.76
     is
    1.74
     your
    1.65
    POSITIVE LOGITS
    𒅎
    2.82
    𒆗
    2.74
    𒉆
    2.74
    𐰣
    2.73
    𒈝
    2.73
    𒊓
    2.72
    𐰢
    2.72
    𒌈
    2.72
    𒀝
    2.71
    𒋙
    2.71
    Activations Density 0.323%

    No Known Activations