© 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. 98424
    Prev
    Next
    INDEX
    Explanations

    citations, links, and final words

    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
    assertFalse
    -1.10
     for
    -0.88
     tega
    -0.85
     better
    -0.84
     fairly
    -0.83
     lebaran
    -0.83
    úrate
    -0.81
     steadily
    -0.78
    Uwaga
    -0.77
     stimm
    -0.77
    POSITIVE LOGITS
     finalement
    0.89
     различ
    0.87
     goto
    0.85
    终于
    0.85
     سعی
    0.84
    終於
    0.82
     -,
    0.82
     "'
    0.82
     Catch
    0.81
     使っ
    0.81
    Activations Density 0.000%

    No Known Activations