© 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. 8366
    Prev
    Next
    INDEX
    Explanations

    description. A.B. file paths

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

    whip

    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
    #[
    0.46
     sp
    0.44
     ruin
    0.43
    Ru
    0.43
     Ruins
    0.42
     Ru
    0.41
    ##
    0.41
     Appreciation
    0.41
     spikes
    0.40
     Report
    0.40
    POSITIVE LOGITS
     гале
    0.49
     galer
    0.48
     whitening
    0.47
     휘
    0.46
     whipping
    0.46
    whale
    0.46
     Whitt
    0.45
    휘
    0.45
     Whiting
    0.44
    짖
    0.44
    Activations Density 0.000%

    No Known Activations