© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5894
    Prev
    Next
    INDEX
    Explanations

    strong negative descriptors

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

    intensifying adverbs

    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
     більше
    0.49
     больше
    0.45
     Appellate
    0.43
     lepší
    0.42
     کرسک
    0.41
     多い
    0.40
     хвати
    0.40
    
    0.39
    悪い
    0.39
     عزیز
    0.39
    POSITIVE LOGITS
     very
    0.87
    very
    0.87
    Very
    0.86
    非常に
    0.81
     extremely
    0.80
     exceedingly
    0.78
     exceptionally
    0.76
    VERY
    0.75
     estremamente
    0.75
     extremamente
    0.75
    Activations Density 0.001%

    No Known Activations