© 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. 15641
    Prev
    Next
    INDEX
    Explanations

    health or

    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
    𝕥
    1.92
    ⼤
    1.59
     Blooms
    1.59
     Salute
    1.58
     buurt
    1.57
    -​
    1.56
    üss
    1.54
    𝓀
    1.53
     Waren
    1.53
    čin
    1.51
    POSITIVE LOGITS
     fork
    1.90
    و
    1.72
    interview
    1.69
     kriv
    1.66
     固定
    1.64
    irani
    1.64
     اسئله
    1.59
     Interview
    1.59
     interview
    1.57
    ფილი
    1.55
    Activations Density 0.072%

    No Known Activations