© 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. 41804
    Prev
    Next
    INDEX
    Explanations

    allows permission to

    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
     trying
    -1.63
    ↵
    -1.49
     also
    -1.47
     they
    -1.47
     going
    -1.43
     protecting
    -1.40
     seemed
    -1.38
     seems
    -1.38
     there
    -1.37
     creating
    -1.34
    POSITIVE LOGITS
     you
    2.64
     réaliser
    1.60
    erialized
    1.55
     SINCE
    1.51
    Its
    1.50
     développer
    1.44
     جميع
    1.44
    #######
    1.43
     étro
    1.43
    </i>
    1.42
    Activations Density 0.050%

    No Known Activations