© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4206
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite

    VRAM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    U
    0.52
    I
    0.50
    X
    0.49
    J
    0.47
    ON
    0.45
    Q
    0.45
    V
    0.45
    B
    0.42
    IS
    0.42
    Z
    0.41
    POSITIVE LOGITS
    ক্ষণের
    0.40
    ruptedException
    0.34
    летним
    0.34
     الحره
    0.33
     tempi
    0.33
    ‶
    0.33
     दिसम्बर
    0.32
     organismos
    0.32
    ಸೂ
    0.32
     wren
    0.32
    Activations Density 0.097%

    No Known Activations