© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1028
    Prev
    Next
    INDEX
    Explanations

    chained Melody

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

    Fight the New Drug

    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
     \"
    0.28
     ОТ
    0.25
    )}=\
    0.24
     darn
    0.24
    IER
    0.23
    plement
    0.22
    AUG
    0.22
    \|
    0.22
    POL
    0.22
     FED
    0.22
    POSITIVE LOGITS
     Sorrow
    0.34
     Blues
    0.33
     Affair
    0.33
     kisses
    0.32
     murders
    0.31
     Wife
    0.30
     sorrows
    0.29
     Conspiracy
    0.28
     Dreams
    0.28
     Girl
    0.28
    Activations Density 0.803%

    No Known Activations