© 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. 75367
    Prev
    Next
    INDEX
    Explanations

    new object instantiation

    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
    cences
    -1.01
    льевич
    -1.01
     Políticas
    -1.01
     Aldi
    -1.01
    魇
    -0.98
    텝
    -0.98
    tehen
    -0.97
     折りたたみ
    -0.96
    alamu
    -0.96
    সূ
    -0.95
    POSITIVE LOGITS
    There
    1.04
    ↵↵↵
    1.02
     any
    1.01
     smaller
    1.01
     small
    0.98
    Before
    0.98
     there
    0.97
     some
    0.97
     two
    0.96
    Now
    0.96
    Activations Density 0.007%

    No Known Activations