© 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. 25764
    Prev
    Next
    INDEX
    Explanations

    related examples or lists

    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
    mektedir
    -0.90
     Bully
    -0.84
     Sula
    -0.81
     FUCK
    -0.80
     yesterday
    -0.79
     grop
    -0.79
     NEM
    -0.78
    rücken
    -0.76
    NEM
    -0.75
     mockery
    -0.73
    POSITIVE LOGITS
    RELATED
    0.89
    Come
    0.83
    Discover
    0.82
     più
    0.79
    Okay
    0.79
     Rel
    0.78
    Want
    0.78
     والس
    0.75
    Rel
    0.74
     RELATED
    0.74
    Activations Density 0.018%

    No Known Activations