© 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. 22-GEMMASCOPE-RES-131K
    7. 98263
    Prev
    Next
    INDEX
    Explanations

    arrival of people

    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
     reele
    -1.02
     rastre
    -0.96
    これも
    -0.88
     persever
    -0.86
    それも
    -0.86
     graduation
    -0.85
    発信
    -0.84
     Removes
    -0.84
     cuyos
    -0.83
    今は
    -0.82
    POSITIVE LOGITS
     addition
    1.16
     joining
    1.15
     arrival
    1.10
    ources
    1.09
     arriving
    1.08
     arrived
    1.05
    replacing
    1.02
    brought
    0.96
     chegada
    0.96
     Addition
    0.95
    Activations Density 0.044%

    No Known Activations