© 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. 34-GEMMASCOPE-RES-131K
    7. 90242
    Prev
    Next
    INDEX
    Explanations

    Samaritan, Samantha, Tamar, Saran, Sarmatian

    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_34/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
    uteness
    -0.75
     CREAM
    -0.74
     tomaron
    -0.73
     lấy
    -0.71
     کو
    -0.70
     encontró
    -0.69
     contemplate
    -0.69
    arken
    -0.68
     fibrin
    -0.68
    に対する
    -0.67
    POSITIVE LOGITS
     Samar
    1.08
     PMP
    0.80
    iskt
    0.79
    PMD
    0.77
    assertion
    0.74
     distillation
    0.74
     TPM
    0.74
    indd
    0.73
    Ʈ
    0.73
     Analyzed
    0.72
    Activations Density 0.022%

    No Known Activations