© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9258
    Prev
    Next
    INDEX
    Explanations

    you'll likely need to

    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
    وں
    1.02
    儁
    0.99
    ﺎ
    0.95
    ڈ
    0.90
    lardı
    0.89
    मेट
    0.87
    presence
    0.86
     presence
    0.84
    ට
    0.84
     देखना
    0.83
    POSITIVE LOGITS
     sorry
    1.19
     thank
    1.06
     разве
    1.05
     forgive
    1.01
     excuse
    1.01
    ibranch
    0.98
     благодар
    0.97
     perdón
    0.97
     Believe
    0.97
     Gracias
    0.95
    Activations Density 0.143%

    No Known Activations