© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11100
    Prev
    Next
    INDEX
    Explanations

    intensifier for adjectives/adverbs

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

    intensifiers followed by varied descriptors

    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_40_width_16k_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
     full
    0.42
     peł
    0.42
     Full
    0.40
     stronger
    0.39
     alcance
    0.39
    赔
    0.39
     TREATMENT
    0.39
    いた
    0.38
    =[],
    0.38
     COMPONENTS
    0.38
    POSITIVE LOGITS
    Totally
    0.61
     unrelated
    0.58
    完全に
    0.56
    totally
    0.56
     totally
    0.55
     полностью
    0.52
    completely
    0.51
     Completely
    0.49
     Totally
    0.48
     innocuous
    0.48
    Activations Density 0.154%

    No Known Activations