© 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. 79984
    Prev
    Next
    INDEX
    Explanations

    Iran unveiled, white morph

    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
     if
    -1.24
     people
    -1.16
    All
    -1.08
     who
    -1.05
     all
    -1.05
    之後
    -1.01
     stylish
    -1.00
     like
    -0.99
    cestor
    -0.95
     każdego
    -0.93
    POSITIVE LOGITS
    Wady
    1.06
    厚的
    1.05
     alcune
    1.02
    かというと
    1.00
    füh
    0.98
    Ār
    0.98
     raggiung
    0.97
    yska
    0.97
     exceptionally
    0.96
     remplissage
    0.95
    Activations Density 0.000%

    No Known Activations