© 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. 76543
    Prev
    Next
    INDEX
    Explanations

    custom and its modifications

    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
     Gegend
    -0.88
     auspices
    -0.85
    lysses
    -0.81
    konstruktion
    -0.80
    Buna
    -0.79
     Nutzung
    -0.79
    pD
    -0.79
     cru
    -0.79
    但不
    -0.79
    Jährige
    -0.78
    POSITIVE LOGITS
    izability
    2.14
    isable
    2.05
    izable
    1.70
    arily
    1.65
     designed
    1.47
    isation
    1.43
    zied
    1.42
    izes
    1.38
     made
    1.34
     created
    1.28
    Activations Density 0.026%

    No Known Activations