© 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. 100159
    Prev
    Next
    INDEX
    Explanations

    box ending code sections

    np_acts-logits-general · gemini-2.5-flash-lite

    LaTeX package names and commands, particularly those related to boxes and layout.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     "
    -1.98
     '
    -1.63
     to
    -1.41
     respectivos
    -1.38
     suele
    -1.37
    しています
    -1.34
     açıklama
    -1.32
     ajang
    -1.30
     solusi
    -1.30
     genießen
    -1.30
    POSITIVE LOGITS
    ஂ
    1.81
     этим
    1.60
     オーバー
    1.59
     rosario
    1.53
    this
    1.52
    這個
    1.52
     perro
    1.52
     Appellants
    1.48
    宬
    1.46
    </b>
    1.45
    Activations Density 0.003%

    No Known Activations