© 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. 9885
    Prev
    Next
    INDEX
    Explanations

    ScScsc

    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
    基づ
    0.93
    klı
    0.91
    nikova
    0.89
    更
    0.88
    の高い
    0.86
    very
    0.86
    মান্ড
    0.85
    lera
    0.84
     línea
    0.83
     réalisée
    0.83
    POSITIVE LOGITS
     warming
    1.29
    warming
    1.19
     Warming
    1.15
     टाइम्स
    1.08
     south
    1.04
    idname
    1.03
    SHARE
    1.03
    暖
    0.99
     মহানগর
    0.96
    范围内
    0.95
    Activations Density 0.042%

    No Known Activations