© 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. 8444
    Prev
    Next
    INDEX
    Explanations

    specific details and updates

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

    positive sentiment and appreciation

    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
     হইত
    0.52
     constituted
    0.52
     constitute
    0.50
    䀎
    0.50
     "'
    0.50
    !!!!!!!!!!!!!!!!
    0.50
     constitutes
    0.49
     Concerning
    0.48
     concerning
    0.48
     inhomogeneous
    0.48
    POSITIVE LOGITS
     kiddos
    1.04
    …..
    0.92
     😉
    0.86
     🥰
    0.86
    ….
    0.85
    ”…
    0.85
     peeps
    0.84
     …..
    0.82
    🤎
    0.81
     aka
    0.81
    Activations Density 0.212%

    No Known Activations