© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2433
    Prev
    Next
    INDEX
    Explanations

    introducing a concept

    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_13_width_65k_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
     b
    1.24
     母
    1.22
     谢
    1.21
     才
    1.21
     judge
    1.20
     fee
    1.20
     CAN
    1.19
     红
    1.17
     restore
    1.16
     メンズ
    1.15
    POSITIVE LOGITS
    Selain
    1.91
    <blockquote>
    1.86
    Pada
    1.85
    Dalam
    1.83
    Jeśli
    1.74
    Menurut
    1.68
    Pokud
    1.65
    På
    1.65
    Jika
    1.63
    În
    1.59
    Activations Density 0.965%

    No Known Activations