© 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. 7029
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

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

    pronouns and verbs

    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
     符合
    0.44
     Jia
    0.43
     righteous
    0.42
     이는
    0.42
     大家
    0.41
    righteous
    0.41
     RMB
    0.40
    丨
    0.40
     想
    0.40
     比
    0.40
    POSITIVE LOGITS
     ..............
    0.54
    ...............
    0.50
    ...........
    0.49
     ..........
    0.47
    ............
    0.45
     Lan
    0.45
    .............
    0.44
     lan
    0.43
    Lan
    0.43
     ........
    0.43
    Activations Density 0.006%

    No Known Activations