© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5945
    Prev
    Next
    INDEX
    Explanations

    Annie, Anne, Annette

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

    Anschlus, anime, Anaconda

    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
    SDLCheck
    0.40
    莒
    0.37
    ेंटीना
    0.37
    wendungen
    0.36
    supportsFocus
    0.36
    slidesPerGroup
    0.35
     BrowserModule
    0.35
    䒴
    0.35
    ﮨ
    0.34
    椹
    0.34
    POSITIVE LOGITS
    <0x8E>
    2.95
     ан
    2.95
     Annie
    2.86
     Ан
    2.84
     Anne
    2.83
     AN
    2.80
    Annie
    2.75
    Anne
    2.72
    アン
    2.63
     Annette
    2.63
    Activations Density 0.377%

    No Known Activations