© 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. 10-GEMMASCOPE-RES-131K
    7. 20251
    Prev
    Next
    INDEX
    Explanations

    tilde paths like `~/`

    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_10/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
    s
    -2.44
    ︳
    -2.28
    )$
    -2.14
    豨
    -2.09
    on
    -2.05
    婬
    -2.03
     naturlig
    -2.02
    龃
    -2.00
    }^{*}\
    -1.96
    的头
    -1.95
    POSITIVE LOGITS
     ‘
    2.42
    In
    2.38
     (‘
    2.28
     в
    2.13
     σε
    2.11
     if
    2.03
    谘
    1.95
    ейчас
    1.94
     {
    1.93
    在他的
    1.92
    Activations Density 0.000%

    No Known Activations