© 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. 7901
    Prev
    Next
    INDEX
    Explanations

    smile playing on lips

    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
    ধে
    0.83
     nigg
    0.82
    ાગ
    0.82
    adata
    0.81
     سره
    0.79
     ब्रे
    0.79
     maint
    0.79
    顾
    0.79
     Ersatz
    0.79
     Keeps
    0.79
    POSITIVE LOGITS
    ahead
    0.97
    correlation
    0.95
    슨
    0.94
     TUN
    0.92
     μέσα
    0.91
    收购
    0.90
     lokalen
    0.90
     いや
    0.89
     tunes
    0.89
    டியில்
    0.88
    Activations Density 0.058%

    No Known Activations