© 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. 12331
    Prev
    Next
    INDEX
    Explanations

    was followed by description

    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
     now
    -1.95
     currently
    -1.66
    now
    -1.27
    currently
    -1.24
     сейчас
    -1.18
    ebly
    -1.14
    tividade
    -1.14
    dicionado
    -1.09
     sekarang
    -1.06
     attualmente
    -1.05
    POSITIVE LOGITS
     kiedyś
    1.21
     later
    1.15
     också
    1.03
     også
    1.01
     после
    1.00
    Mutability
    0.99
     позже
    0.98
    Later
    0.96
     before
    0.95
     myös
    0.95
    Activations Density 0.114%

    No Known Activations