© 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. 12989
    Prev
    Next
    INDEX
    Explanations

    more effectively

    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
     tyl
    2.13
     substantial
    1.95
    ‐
    1.82
     alqu
    1.78
     puțin
    1.77
    ケーション
    1.77
    ('./
    1.74
     組
    1.74
    рку
    1.73
     vài
    1.70
    POSITIVE LOGITS
    又要
    1.63
    respond
    1.49
    झा
    1.45
    解放
    1.45
    controlling
    1.38
    ************
    1.37
    fohlen
    1.37
    edly
    1.36
    Zj
    1.36
     نعمت
    1.34
    Activations Density 0.068%

    No Known Activations