© 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. 7665
    Prev
    Next
    INDEX
    Explanations

    Scalability and calibrated

    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
    Ｗ
    0.95
    सा
    0.89
    渥
    0.87
    ｵ
    0.86
    ፎ
    0.84
    ценка
    0.82
    चर
    0.80
    ட
    0.79
    ˇ
    0.79
    चौ
    0.78
    POSITIVE LOGITS
     shumë
    1.99
     për
    1.93
     të
    1.92
     në
    1.91
     që
    1.90
     një
    1.88
     është
    1.77
     pë
    1.74
     janë
    1.74
     edhe
    1.73
    Activations Density 0.022%

    No Known Activations