© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 560
    Prev
    Next
    INDEX
    Explanations

    bubbles and air

    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
    𒌑
    2.16
    𒆷
    2.06
    𒄀
    2.03
    𒃻
    2.03
    𒅎
    2.01
    𐰢
    2.00
    𐰖
    1.99
    𒈪
    1.99
    𐰑
    1.97
    𒊑
    1.95
    POSITIVE LOGITS
    .
    1.68
     in
    1.64
     of
    1.59
     and
    1.51
     for
    1.51
    ,
    1.48
     from
    1.46
     with
    1.44
    /
    1.37
     was
    1.36
    Activations Density 3.546%

    No Known Activations