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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10782
    Prev
    Next
    INDEX
    Explanations

    community based organizations

    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
     १००
    1.02
    готовка
    1.00
     mitad
    0.98
    ုပ်တို့
    0.97
     सलाह
    0.95
    教程
    0.95
    ⅓
    0.92
    三十
    0.90
     ½
    0.89
    र्नल
    0.88
    POSITIVE LOGITS
    itements
    1.05
     just
    0.97
    just
    0.88
    <0xB2>
    0.86
     some
    0.83
     revamped
    0.83
     merely
    0.80
    poco
    0.80
    }}>
    0.80
     above
    0.80
    Activations Density 0.067%

    No Known Activations