© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32734
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

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

    contrast and conclusion introducers

    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_262k_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
    ুরি
    0.51
    শিকান্ত
    0.47
    repository
    0.46
    রন
    0.45
    YYYY
    0.44
    χρι
    0.44
     %><%=
    0.44
    ଉ
    0.43
     robberies
    0.43
    ႅ
    0.43
    POSITIVE LOGITS
     Nevertheless
    0.85
     Nonetheless
    0.79
     However
    0.69
     But
    0.63
     Ancak
    0.63
     Cependant
    0.59
     nonetheless
    0.58
    Nonetheless
    0.58
    Nevertheless
    0.57
     Tuttavia
    0.57
    Activations Density 0.002%

    No Known Activations