© 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. 10-GEMMASCOPE-RES-131K
    7. 85578
    Prev
    Next
    INDEX
    Explanations

    past participles and verbs

    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_10/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
    揶
    -2.41
    やってる
    -2.36
    捋
    -2.33
    悩む
    -2.14
    記入
    -2.13
    描いて
    -2.09
    呟
    -2.09
    粜
    -2.08
     lässt
    -2.08
    踱
    -2.05
    POSITIVE LOGITS
    These
    2.42
    Also
    2.16
    هاي
    2.13
     sebelumnya
    2.13
    珖
    2.11
    .
    2.09
    However
    2.06
    歲
    2.02
     также
    1.94
     luglio
    1.94
    Activations Density 0.002%

    No Known Activations