© 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. 59087
    Prev
    Next
    INDEX
    Explanations

    Tap, mock, Super

    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
     أخ
    -0.79
     همچ
    -0.77
     наве
    -0.75
     سين
    -0.74
     Ä
    -0.73
     Cune
    -0.73
     agitation
    -0.70
     TEACH
    -0.69
    ilst
    -0.69
     perma
    -0.68
    POSITIVE LOGITS
     mock
    0.97
    Mock
    0.86
    kapet
    0.82
    Wellington
    0.80
     Wellington
    0.79
     Nand
    0.79
    千年
    0.74
    mikro
    0.73
    mock
    0.71
    MOCK
    0.71
    Activations Density 0.012%

    No Known Activations