© 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. 48186
    Prev
    Next
    INDEX
    Explanations

    path quotes workers evolution : GORDON

    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
    adto
    -0.86
     surveys
    -0.85
    Nachdem
    -0.84
     III
    -0.82
     HELP
    -0.81
    averaged
    -0.81
     Surveys
    -0.79
    weif
    -0.78
    Damit
    -0.76
     help
    -0.76
    POSITIVE LOGITS
     Muchos
    0.81
    towanie
    0.81
     Agreg
    0.77
    sedur
    0.77
     糖
    0.76
    masuk
    0.76
    losing
    0.75
    duled
    0.75
    נוּ
    0.75
     Lived
    0.75
    Activations Density 0.000%

    No Known Activations