© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59896
    Prev
    Next
    INDEX
    Explanations

    country music and charts

    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
    mosa
    -0.77
    activ
    -0.74
     implantation
    -0.73
    Warriors
    -0.71
    úb
    -0.71
    kok
    -0.68
    講
    -0.68
     warriors
    -0.68
    惠
    -0.67
     Brah
    -0.67
    POSITIVE LOGITS
     Hee
    0.89
     Nashville
    0.86
    ☍
    0.82
    Nashville
    0.81
    Hee
    0.81
    cerely
    0.80
    bsen
    0.79
     llan
    0.77
     acorde
    0.77
    CONTR
    0.76
    Activations Density 0.027%

    No Known Activations