© 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. 34752
    Prev
    Next
    INDEX
    Explanations

    links and code structures

    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
    <eos>
    -1.53
     ͜
    -0.80
     GO
    -0.79
    ましたが
    -0.78
    奕
    -0.76
    тся
    -0.76
    alese
    -0.75
    䨻
    -0.75
    дея
    -0.73
     Harp
    -0.73
    POSITIVE LOGITS
    +#+
    0.90
    timme
    0.85
    ↵↵↵↵↵↵↵↵↵↵↵
    0.83
    ↵↵↵↵↵↵↵↵↵↵
    0.81
     discriminant
    0.79
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.79
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.76
     derelict
    0.76
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.75
     настолько
    0.75
    Activations Density 0.783%

    No Known Activations