© 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. 17859
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives

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

    storytelling

    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
     btw
    0.47
     ""
    0.45
     aproximadamente
    0.44
    我在
    0.44
     BTW
    0.43
    बॉलीवुड
    0.43
     CIRCA
    0.43
    ⏰
    0.43
     ''
    0.42
    में
    0.41
    POSITIVE LOGITS
    十九
    0.49
     Deviation
    0.48
     Descriptions
    0.46
     fourteen
    0.46
     eighty
    0.44
    Descriptions
    0.44
     Fiction
    0.43
     thirteen
    0.42
     strengthened
    0.41
     nineteen
    0.41
    Activations Density 0.012%

    No Known Activations