© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36723
    Prev
    Next
    INDEX
    Explanations

    containing options and arguments

    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_22/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
     before
    -1.24
     while
    -1.23
     this
    -1.13
    falen
    -1.12
    favicon
    -1.05
     ενώ
    -1.04
     δεν
    -1.02
     disparos
    -1.02
     pensar
    -0.98
     even
    -0.98
    POSITIVE LOGITS
     containing
    1.09
     contains
    1.04
    ブー
    1.00
    は以下の
    0.99
     Луч
    0.98
     consisting
    0.98
     *@
    0.98
    BAST
    0.96
     consists
    0.95
    馒
    0.95
    Activations Density 0.083%

    No Known Activations