© 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. 12256
    Prev
    Next
    INDEX
    Explanations

    afternoon scheduled activities

    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
     '[
    1.75
     is
    1.60
     has
    1.59
     was
    1.58
    anov
    1.56
     indietro
    1.54
     Scene
    1.54
    ,'
    1.51
     ago
    1.48
    下了
    1.48
    POSITIVE LOGITS
    𝐦
    2.42
    𝐢
    2.31
    𝐨
    2.23
    𝐩
    2.12
    𝐞
    2.09
     ph
    2.04
    𝐥
    2.02
    𝐠
    2.02
    𝐛
    2.01
    𝐮
    1.99
    Activations Density 0.045%

    No Known Activations