© 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. 21752
    Prev
    Next
    INDEX
    Explanations

    cooking instructions

    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
     or
    -2.09
     it
    -1.87
     but
    -1.81
     there
    -1.55
     of
    -1.54
    ModelMap
    -1.53
    though
    -1.48
     nhưng
    -1.47
     was
    -1.45
     which
    -1.44
    POSITIVE LOGITS
     attente
    1.82
     ruban
    1.57
     exprim
    1.55
     another
    1.53
     désert
    1.48
    뗄
    1.47
     gardien
    1.44
     plancher
    1.43
     trésor
    1.42
    ANTES
    1.41
    Activations Density 0.008%

    No Known Activations