© 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. 3055
    Prev
    Next
    INDEX
    Explanations

    informal or non-standard language

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

    knowledge as a system

    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
    ❣️
    0.66
    😊
    0.61
    :-)
    0.60
     …..
    0.59
     ….
    0.56
    いろいろ
    0.56
     ..,
    0.55
     …….
    0.55
    ‥
    0.55
    ᆢ
    0.55
    POSITIVE LOGITS
     whilst
    0.84
     Whilst
    0.79
     recieved
    0.77
     ибо
    0.77
    Whilst
    0.75
     aswell
    0.75
     recieve
    0.75
     aforementioned
    0.71
     lmao
    0.70
     seperate
    0.70
    Activations Density 0.525%

    No Known Activations