© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 25
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions followed by punctuation

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

    transition words followed by punctuation

    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_31_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
     illetve
    0.21
     takže
    0.20
     inital
    0.19
     そして
    0.19
     initialize
    0.18
     sparsim
    0.18
    }/>
    0.17
     "))
    0.17
    หรือ
    0.17
     initialise
    0.17
    POSITIVE LOGITS
    ،
    0.52
    ,
    0.48
    ，
    0.45
    ၊
    0.45
    、
    0.38
    ,,
    0.35
    ፣
    0.35
    ¸
    0.32
    ，《
    0.30
    ,-
    0.30
    Activations Density 1.199%

    No Known Activations