© 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. 10-GEMMASCOPE-RES-131K
    4. 19
    Prev
    Next
    INDEX
    Explanations

    Golden Globes and awards

    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
     While
    -1.68
    x
    -1.67
    It
    -1.67
    While
    -1.66
     Despite
    -1.66
    After
    -1.62
     When
    -1.58
     Although
    -1.55
    When
    -1.54
     Since
    -1.53
    POSITIVE LOGITS
     pères
    1.56
     chrétiens
    1.41
    kredit
    1.39
    merksam
    1.38
    cardname
    1.37
    kabel
    1.36
    Answered
    1.36
    ㅁ
    1.34
    Wady
    1.34
     kupa
    1.30
    Activations Density 0.010%

    No Known Activations