© 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. 60013
    Prev
    Next
    INDEX
    Explanations

    input signals or data

    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
    ⓪
    -0.77
     fauna
    -0.73
     البريط
    -0.73
    暂停
    -0.71
     розмі
    -0.71
    TopLevel
    -0.71
    剜
    -0.71
    ]<
    -0.71
    拴
    -0.70
    vanie
    -0.69
    POSITIVE LOGITS
     inputs
    1.24
     input
    1.09
     queries
    0.93
    input
    0.92
     incoming
    0.91
    输入
    0.90
    لاج
    0.90
    query
    0.89
     Input
    0.88
    جير
    0.88
    Activations Density 0.009%

    No Known Activations