© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102577
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and assignments

    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
     messen
    -0.82
     fruta
    -0.82
    )](
    -0.78
     opinión
    -0.75
     these
    -0.74
     indican
    -0.74
     tanda
    -0.73
    しつつ
    -0.73
     передний
    -0.72
    регистри
    -0.71
    POSITIVE LOGITS
    μφ
    0.85
    explo
    0.81
    américa
    0.79
     echocardio
    0.77
    רְ
    0.77
     fasti
    0.77
     pairwise
    0.75
    给人
    0.75
     Whitman
    0.75
     campagne
    0.75
    Activations Density 0.003%

    No Known Activations