© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128482
    Prev
    Next
    INDEX
    Explanations

    furlongs and distances

    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
    ейчас
    -1.59
     mikina
    -1.52
    ⚢
    -1.49
    plantas
    -1.43
     réfrig
    -1.43
    􏰁
    -1.41
     mortem
    -1.39
     pels
    -1.38
    ".
    -1.37
    
    -1.37
    POSITIVE LOGITS
    ?
    1.80
     could
    1.71
        
    1.58
     With
    1.46
     don
    1.39
     should
    1.39
     like
    1.37
     only
    1.35
     may
    1.35
     :
    1.35
    Activations Density 0.009%

    No Known Activations