© 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. 107104
    Prev
    Next
    INDEX
    Explanations

    to infinitive 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_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
     напа
    -0.89
    lit
    -0.88
     sabia
    -0.87
     to
    -0.85
    รู้
    -0.85
     PAYMENT
    -0.84
    きん
    -0.84
    ђа
    -0.84
    wechat
    -0.84
     conducted
    -0.84
    POSITIVE LOGITS
     azonban
    1.17
    !",
    1.02
    During
    1.00
    Şi
    1.00
    忪
    0.96
    Leírás
    0.94
    While
    0.94
     both
    0.93
    >),
    0.93
    ?”,
    0.91
    Activations Density 0.052%

    No Known Activations