© 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. 14621
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens representing decimal numbers (floating‐point values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     hilfre
    -1.71
     řekl
    -1.66
    谁能
    -1.47
    很赞
    -1.44
     ausreich
    -1.44
     vielfäl
    -1.43
     notwendi
    -1.41
     Auffassung
    -1.41
    經常
    -1.40
     gröss
    -1.40
    POSITIVE LOGITS
     jeweils
    1.54
     "..\..\
    1.53
     nationales
    1.41
    苤
    1.39
    kkel
    1.38
     tenues
    1.37
     elegante
    1.35
     sabes
    1.34
    weile
    1.34
    ributes
    1.33
    Activations Density 0.006%

    No Known Activations