© 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. 10-GEMMASCOPE-RES-131K
    7. 70711
    Prev
    Next
    INDEX
    Explanations

    whew, relief, sighs

    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_10/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
     their
    -2.05
     WHY
    -1.69
    I
    -1.67
     WHAT
    -1.63
     whats
    -1.59
     relacionadas
    -1.44
    H
    -1.41
    ⃣
    -1.40
    G
    -1.40
     bzw
    -1.40
    POSITIVE LOGITS
    以免
    1.82
    ilets
    1.80
    了
    1.78
    籥
    1.74
    AIRES
    1.69
     vernac
    1.67
    thansa
    1.65
     contiennent
    1.64
     ciment
    1.64
     alamu
    1.62
    Activations Density 0.005%

    No Known Activations