© 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. 1778
    Prev
    Next
    INDEX
    Explanations

    categorized by effort

    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
     dragState
    2.78
    十叁章
    2.78
    晠
    2.75
     kehnd
    2.74
     strListName
    2.68
    十壹章
    2.68
    apetva
    2.68
     saddas
    2.64
     pavattati
    2.63
     payog
    2.62
    POSITIVE LOGITS
    -
    1.99
    ¬
    1.78
    ­
    1.68
    г
    1.64
    ib
    1.64
    с
    1.63
    ag
    1.53
    ip
    1.53
    att
    1.49
    ‑
    1.47
    Activations Density 2.808%

    No Known Activations