© 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. 844
    Prev
    Next
    INDEX
    Explanations

    specifies the main aspect

    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
     semua
    -1.91
     I
    -1.76
     baloncesto
    -1.70
     we
    -1.63
     as
    -1.59
     anche
    -1.59
     aussi
    -1.55
     auch
    -1.52
     or
    -1.49
     +"
    -1.48
    POSITIVE LOGITS
     aveo
    1.91
     iveco
    1.78
     kangoo
    1.70
     riusc
    1.67
    ))$_
    1.64
    푣
    1.64
     sorento
    1.61
     tulum
    1.60
     vitara
    1.60
    アルミ
    1.60
    Activations Density 0.115%

    No Known Activations