© 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. 4524
    Prev
    Next
    INDEX
    Explanations

    kind or type

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

    what types of

    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
    okeh
    0.37
    AppCompatTheme
    0.35
     Majka
    0.35
    結晶
    0.34
     व्यवस्थित
    0.34
    ccncc
    0.34
    ερο
    0.34
    엊
    0.34
    भूमी
    0.33
    န်း
    0.32
    POSITIVE LOGITS
     kind
    3.53
     type
    3.48
     kinds
    3.45
     tipo
    3.27
     نوع
    3.27
     types
    3.25
     jenis
    3.25
    kinds
    3.11
     loại
    3.05
     soort
    2.97
    Activations Density 0.501%

    No Known Activations