© 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. 87389
    Prev
    Next
    INDEX
    Explanations

    matrix representation

    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
    
    -1.83
    Algérie
    -1.79
    谷川
    -1.66
     anfangen
    -1.58
    思議
    -1.56
    @[+][
    -1.55
    的看着
    -1.55
    大量
    -1.55
    maßnahmen
    -1.55
    lierte
    -1.55
    POSITIVE LOGITS
     the
    2.16
    _
    1.75
     these
    1.66
     createDate
    1.59
     it
    1.56
     following
    1.48
     now
    1.44
     Nachdem
    1.43
    ‐
    1.42
    щихся
    1.38
    Activations Density 0.021%

    No Known Activations