© 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. 10-GEMMASCOPE-RES-131K
    7. 10173
    Prev
    Next
    INDEX
    Explanations

    identifying descriptive statements

    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
     with
    -2.19
     Some
    -1.65
     which
    -1.62
     in
    -1.59
     Actually
    -1.54
     nessuna
    -1.54
     Generally
    -1.48
          
    -1.47
     say
    -1.46
     selves
    -1.38
    POSITIVE LOGITS
    いかがでしたか
    1.94
    どうやら
    1.78
    僕も
    1.70
    过去的
    1.61
     ralenti
    1.60
     iki
    1.59
     decorativa
    1.58
    formerly
    1.57
    こだわり
    1.55
     metoda
    1.55
    Activations Density 0.069%

    No Known Activations