© 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. 7662
    Prev
    Next
    INDEX
    Explanations

    spending time on 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_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
     M
    1.23
     ligt
    1.20
     obras
    1.19
    will
    1.18
     mérite
    1.18
     touche
    1.16
     খান
    1.16
     œuvres
    1.14
    ab
    1.14
    은
    1.14
    POSITIVE LOGITS
     putting
    3.39
     obtaining
    3.34
     establishing
    3.33
     making
    3.28
     getting
    3.24
     erecting
    3.23
     possessing
    3.21
     selecting
    3.20
     completing
    3.19
     eliminating
    3.18
    Activations Density 0.701%

    No Known Activations