© 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. 74
    Prev
    Next
    INDEX
    Explanations

    but introduces contrast or exception

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

    but followed by pronoun or article

    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
    ،
    0.21
    ，
    0.19
    、
    0.19
    の
    0.18
     ℝ
    0.17
    $\--
    0.17
     پیسو
    0.17
     ferroc
    0.17
    의
    0.17
    ፣
    0.17
    POSITIVE LOGITS
    that
    0.22
    ting
    0.22
     didn
    0.21
     dennoch
    0.20
    tere
    0.20
    लेकिन
    0.20
    not
    0.19
     doesn
    0.19
     ikke
    0.19
     তবুও
    0.19
    Activations Density 0.693%

    No Known Activations