© 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. 49856
    Prev
    Next
    INDEX
    Explanations

    additional file information

    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
     Sach
    -0.76
    obat
    -0.72
    tifik
    -0.69
    BINDING
    -0.68
     シングル
    -0.67
     Hawkins
    -0.65
    heartbeat
    -0.65
    BOSTON
    -0.65
    khid
    -0.64
    왠
    -0.64
    POSITIVE LOGITS
     Ursachen
    0.71
    ETTE
    0.69
    丞
    0.68
     wizards
    0.65
    ())
    0.65
    ara
    0.65
    ൂ
    0.64
     Mae
    0.64
    NET
    0.63
    тъ
    0.63
    Activations Density 0.093%

    No Known Activations