© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8196
    Prev
    Next
    INDEX
    Explanations

    career paths and advice

    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_22_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
    eltzer
    0.93
    JobID
    0.90
     प्रतिदिन
    0.84
    タニ
    0.84
    ණ
    0.84
    名叫
    0.82
    productions
    0.81
    тику
    0.81
    ⑸
    0.81
    HomeController
    0.80
    POSITIVE LOGITS
     path
    1.53
     paths
    1.49
     Paths
    1.32
     Path
    1.25
    paths
    1.24
    path
    1.19
     pathway
    1.18
    道路
    1.17
     路
    1.16
    路
    1.14
    Activations Density 0.072%

    No Known Activations