© 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. 3583
    Prev
    Next
    INDEX
    Explanations

    running python, c, or cpp code

    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
     ١
    1.93
     ૩
    1.78
     ٣
    1.77
     來
    1.63
     ٢
    1.60
     餐
    1.59
     방식
    1.59
     跟
    1.54
     한
    1.53
     এক
    1.53
    POSITIVE LOGITS
     Abgerufen
    1.26
     rayonnement
    1.24
     mesmas
    1.24
     erstmals
    1.21
     merda
    1.19
     épu
    1.18
     morreu
    1.18
     própria
    1.17
     muere
    1.17
     stesse
    1.16
    Activations Density 0.001%

    No Known Activations