© 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. 118131
    Prev
    Next
    INDEX
    Explanations

    firstly, however, originally

    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
     также
    -1.45
     also
    -1.41
     наконец
    -1.41
     lastly
    -1.27
     także
    -1.20
    なお
    -1.20
     finalmente
    -1.19
    Lastly
    -1.16
    最后
    -1.09
     даже
    -1.08
    POSITIVE LOGITS
    Firstly
    1.39
    首先
    1.16
     Firstly
    1.10
     It
    1.07
     first
    1.06
     ilk
    1.04
     FIRST
    1.02
    继续阅读
    1.02
     Instead
    1.02
    However
    1.02
    Activations Density 0.193%

    No Known Activations