© 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. 53574
    Prev
    Next
    INDEX
    Explanations

    not only

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

    not only... but also

    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
     যদিও
    0.48
    although
    0.46
     nonetheless
    0.46
    ։
    0.46
     हालांकि
    0.46
     jednak
    0.44
     néanmoins
    0.43
    tests
    0.43
     tuttavia
    0.43
     entanto
    0.43
    POSITIVE LOGITS
     sondern
    0.79
     बल्कि
    0.76
     بلکه
    0.69
    而是
    0.67
    뿐
    0.66
     بلکہ
    0.65
     뿐
    0.63
     മാത്രമല്ല
    0.63
    だけでなく
    0.61
     sino
    0.59
    Activations Density 0.077%

    No Known Activations