© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43281
    Prev
    Next
    INDEX
    Explanations

    continuing an action or state

    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
     time
    -1.67
     also
    -1.64
     about
    -1.56
     undeniably
    -1.53
     may
    -1.52
     these
    -1.49
     Also
    -1.47
     With
    -1.45
    Also
    -1.45
     before
    -1.44
    POSITIVE LOGITS
     appris
    1.57
     poursuivre
    1.56
    を含
    1.31
     sooo
    1.29
     ванной
    1.29
     sauf
    1.29
     唯美
    1.29
    
    1.29
    hopefully
    1.28
    跸
    1.28
    Activations Density 0.063%

    No Known Activations