© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85970
    Prev
    Next
    INDEX
    Explanations

    state verbs followed by complement

    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
     that
    -1.29
     new
    -1.27
     now
    -1.21
     --
    -1.18
     얻
    -1.16
     each
    -1.16
     —
    -1.15
     should
    -1.15
     obviously
    -1.15
     they
    -1.11
    POSITIVE LOGITS
    objectives
    1.24
     vous
    1.20
    GPT
    1.19
    룽
    1.17
    moda
    1.17
    付けた
    1.17
     acab
    1.16
    独特的
    1.16
    媲
    1.16
    entait
    1.15
    Activations Density 0.048%

    No Known Activations