© 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. 103271
    Prev
    Next
    INDEX
    Explanations

    words starting with sta

    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
     The
    -4.00
     Then
    -2.70
     ältere
    -2.61
     zwölf
    -2.58
     Our
    -2.55
    .
    -2.48
     beinahe
    -2.45
    違う
    -2.44
     übri
    -2.41
    л
    -2.36
    POSITIVE LOGITS
    your
    2.70
    涠
    2.66
    
    2.64
     sentier
    2.61
     pourcentage
    2.59
     avantage
    2.56
     ouverture
    2.55
    卨
    2.53
     arbre
    2.50
     escalier
    2.48
    Activations Density 0.013%

    No Known Activations