© 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. 107734
    Prev
    Next
    INDEX
    Explanations

    national parks and RM

    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
    Acting
    -0.82
    ţei
    -0.78
    賁
    -0.73
     Acting
    -0.72
     acting
    -0.72
    ownie
    -0.71
    orchid
    -0.71
    teo
    -0.70
     bertindak
    -0.70
    Kow
    -0.69
    POSITIVE LOGITS
    റ്റ
    0.83
    tick
    0.78
    druck
    0.76
    кового
    0.76
     CFR
    0.73
     Recommended
    0.72
     夏
    0.72
     sirven
    0.71
     Distinguished
    0.71
     ваши
    0.71
    Activations Density 0.005%

    No Known Activations