© 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. 18003
    Prev
    Next
    INDEX
    Explanations

    K. Kensington

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

    Inner Mongolia

    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
     ছ
    0.46
     ца
    0.45
     والص
    0.44
     Цуки
    0.42
    َص
    0.40
    曹
    0.40
     Cai
    0.39
    hotite
    0.39
    <0x83>
    0.39
    RxDocument
    0.38
    POSITIVE LOGITS
     KC
    2.27
     KP
    2.27
     KF
    2.27
     KB
    2.25
     KT
    2.17
     KD
    2.16
    KC
    2.16
    KP
    2.13
    KF
    2.13
     KM
    2.06
    Activations Density 0.856%

    No Known Activations