© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11297
    Prev
    Next
    INDEX
    Explanations

    then what happens next

    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_22/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
    柘
    -1.34
     every
    -1.05
     empfind
    -1.02
     distanci
    -1.00
     atualmente
    -0.98
     Estamos
    -0.98
     сейчас
    -0.98
    都已经
    -0.96
     actuellement
    -0.96
    سف
    -0.94
    POSITIVE LOGITS
     then
    3.58
    then
    1.98
    Then
    1.94
     wtedy
    1.90
     entonces
    1.82
     Then
    1.74
     biasanya
    1.71
     usually
    1.71
     dann
    1.66
     kemudian
    1.63
    Activations Density 0.106%

    No Known Activations