© 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. 34-GEMMASCOPE-RES-131K
    7. 33660
    Prev
    Next
    INDEX
    Explanations

    html option elements

    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
    vér
    -0.82
    ]<
    -0.79
     başka
    -0.75
    넣
    -0.75
    }<
    -0.75
    quese
    -0.75
    PCell
    -0.74
    áneos
    -0.74
    FailureListener
    -0.71
    "><
    -0.71
    POSITIVE LOGITS
     value
    2.05
     selected
    1.64
    selected
    1.33
    value
    1.27
     Selected
    1.25
     Value
    1.23
    SELECTED
    1.20
     values
    1.17
    Selected
    1.14
     SELECTED
    1.13
    Activations Density 0.005%

    No Known Activations