© 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. 64084
    Prev
    Next
    INDEX
    Explanations

    verbs ending in ing

    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
    もう一度
    -1.14
    Ensuite
    -1.13
     många
    -1.13
     quickly
    -1.11
     nochmal
    -1.06
     commencing
    -1.05
     纹理
    -1.04
    Intial
    -1.02
     some
    -1.02
    splitContainer
    -1.02
    POSITIVE LOGITS
     and
    1.62
    下去
    1.43
     until
    1.39
     même
    1.28
     despite
    1.24
     المزيد
    1.20
     even
    1.09
    直到
    1.05
     bahkan
    1.05
    どんどん
    1.04
    Activations Density 0.040%

    No Known Activations