© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108013
    Prev
    Next
    INDEX
    Explanations

    not only... but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rather
    -1.30
     ainda
    -1.09
     Rather
    -1.07
    : 
    -1.07
    ificantly
    -1.04
     vraiment
    -1.02
    ,
    -1.00
     سایر
    -0.98
     autres
    -0.96
    外部連結
    -0.96
    POSITIVE LOGITS
     just
    2.64
     only
    2.63
     только
    1.45
    just
    1.42
     merely
    1.41
     فقط
    1.41
    Just
    1.39
     μόνο
    1.39
     because
    1.30
    只是一
    1.28
    Activations Density 0.013%

    No Known Activations