© 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. 65860
    Prev
    Next
    INDEX
    Explanations

    package names and Java code

    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
    ''');
    -1.11
     }}">
    -1.11
    +");
    -1.09
    BindingResult
    -1.08
    andafter
    -1.07
     EventArgs
    -1.07
    $.}
    -1.05
    MultipartFile
    -1.05
    //{
    -1.04
    signable
    -1.04
    POSITIVE LOGITS
     proletariat
    0.98
    acabana
    0.93
     zulassen
    0.91
    걸
    0.91
    ㄋ
    0.91
    ilions
    0.88
     wiederhol
    0.87
     ansehen
    0.86
     gegenwär
    0.86
     hypnosis
    0.86
    Activations Density 0.023%

    No Known Activations