© 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. 8757
    Prev
    Next
    INDEX
    Explanations

    LSU Tigers

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

    can find

    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
    𐰢
    0.44
    ToSend
    0.42
     Johannes
    0.40
     defineConfig
    0.40
    NERVE
    0.39
    Joan
    0.39
     Joan
    0.39
    ⤟
    0.39
    DebugSymbols
    0.38
    갤럭
    0.38
    POSITIVE LOGITS
     fr
    0.82
     LSU
    0.77
    fr
    0.74
    Fr
    0.73
     Fr
    0.69
     FR
    0.67
     फ्र
    0.65
     tiger
    0.64
     فر
    0.64
    Tiger
    0.62
    Activations Density 0.003%

    No Known Activations