© 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. 75389
    Prev
    Next
    INDEX
    Explanations

    little items

    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
     stör
    -1.63
    
    -1.58
    Ấ
    -1.50
    tualmente
    -1.49
     sufficient
    -1.49
    ꉂ
    -1.48
     and
    -1.45
    ⽌
    -1.44
     värld
    -1.44
     louer
    -1.41
    POSITIVE LOGITS
     they
    1.55
    随即
    1.54
     little
    1.50
    }();
    1.48
     мы
    1.48
     —
    1.44
     «
    1.41
    いかがでしたか
    1.41
     bit
    1.40
     of
    1.38
    Activations Density 0.024%

    No Known Activations