© 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. 21958
    Prev
    Next
    INDEX
    Explanations

    vs. comparisons

    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
     incrí
    -1.85
     GRATU
    -1.84
    毟
    -1.80
     perche
    -1.79
    lize
    -1.75
     incendie
    -1.75
     optik
    -1.73
    ifies
    -1.71
    lizes
    -1.70
     recev
    -1.69
    POSITIVE LOGITS
     about
    2.56
     two
    1.74
    </h2>
    1.68
     using
    1.56
     M
    1.55
     part
    1.52
     Makes
    1.48
     E
    1.46
     D
    1.45
     act
    1.44
    Activations Density 0.163%

    No Known Activations