© 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. 45273
    Prev
    Next
    INDEX
    Explanations

    Q: or Interview:

    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
    なんと
    -0.77
    是非常
    -0.77
    abonnement
    -0.74
    መ
    -0.74
     тө
    -0.74
    Amical
    -0.73
    Passengers
    -0.72
     shelters
    -0.72
    Paulo
    -0.71
     Дер
    -0.71
    POSITIVE LOGITS
     zari
    0.78
    但是
    0.77
    Akt
    0.77
    ∮
    0.77
    Rl
    0.74
    ſ
    0.73
     затем
    0.73
    Ol
    0.72
    օ
    0.72
    tii
    0.72
    Activations Density 0.022%

    No Known Activations