© 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. 2849
    Prev
    Next
    INDEX
    Explanations

    numbers in contexts of time or quantity

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

    DoorDash

    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
     CANT
    0.47
     mystery
    0.45
     Uncertainty
    0.42
     uncertainty
    0.40
     PROBLEM
    0.40
    mystery
    0.40
     sacs
    0.39
    ﮕ
    0.39
     Cant
    0.38
    BIG
    0.38
    POSITIVE LOGITS
     getVideo
    0.47
     도움
    0.45
     Minuten
    0.44
     دقیقه
    0.42
     помо
    0.42
     minutes
    0.41
     ayuda
    0.41
     minuto
    0.41
     विज्ञापन
    0.40
    show
    0.40
    Activations Density 0.000%

    No Known Activations