© 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. 92505
    Prev
    Next
    INDEX
    Explanations

    public records requests and fees

    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
    congress
    -0.85
    diplom
    -0.83
    巌
    -0.82
     Congress
    -0.78
    Juri
    -0.75
     congress
    -0.75
    Pinned
    -0.74
    Lähteet
    -0.74
     trọng
    -0.73
    dialect
    -0.72
    POSITIVE LOGITS
     records
    1.65
     public
    1.42
     Records
    1.41
    Records
    1.39
    records
    1.38
     Public
    1.34
    Public
    1.33
     open
    1.26
    open
    1.14
    Open
    1.10
    Activations Density 0.025%

    No Known Activations