© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112143
    Prev
    Next
    INDEX
    Explanations

    @Override

    np_acts-logits-general · gemini-2.5-flash-lite

    the `@Override` annotation in Java/Android code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     are
    -1.89
    逡
    -1.88
    alakip
    -1.74
    Beskrivning
    -1.65
     nejen
    -1.56
     includes
    -1.52
    ?"
    -1.51
     提示
    -1.48
     including
    -1.47
     conferencias
    -1.47
    POSITIVE LOGITS
    “
    1.63
     “
    1.57
     頭
    1.43
    <td>
    1.37
     gebra
    1.36
    of
    1.36
     farb
    1.27
     другую
    1.24
    atological
    1.21
     kha
    1.20
    Activations Density 0.002%

    No Known Activations