© 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. 33440
    Prev
    Next
    INDEX
    Explanations

    deconstructs and court cases

    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
    <bos>
    -0.90
    Matic
    -0.75
    matic
    -0.75
    leted
    -0.75
    ering
    -0.69
    plor
    -0.69
    与此同时
    -0.68
    ？」
    -0.67
     potent
    -0.67
    кладка
    -0.67
    POSITIVE LOGITS
     demostra
    0.88
     démon
    0.83
    ELDS
    0.83
    Enjoy
    0.83
    estructura
    0.82
    ленных
    0.79
    にします
    0.77
    Aceptar
    0.77
    訕
    0.77
    Aim
    0.76
    Activations Density 0.002%

    No Known Activations