© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10097
    Prev
    Next
    INDEX
    Explanations

    adding

    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
    近平
    1.10
    mnf
    1.00
    波動
    0.96
    巡
    0.94
    ilización
    0.92
    展開
    0.90
    准
    0.90
    NCc
    0.89
    reif
    0.88
    =/
    0.88
    POSITIVE LOGITS
     addition
    4.26
     add
    4.22
     added
    4.11
     Add
    4.00
     additions
    3.97
    add
    3.93
    Add
    3.92
     Addition
    3.87
     adding
    3.83
    added
    3.82
    Activations Density 0.835%

    No Known Activations