© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99699
    Prev
    Next
    INDEX
    Explanations

    Effect of, Late complications of, Recovery of

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

    The neuron fires on occurrences of “jadx,” i.e. references to the Jadx APK decompiler.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    </h3>
    -2.13
     \""
    -2.05
    żeli
    -2.02
    }
    -2.00
    !");
    -1.94
    </td>
    -1.84
    }{
    -1.82
     „
    -1.79
     It
    -1.78
    тение
    -1.77
    POSITIVE LOGITS
    to
    2.58
    
    2.36
    1
    2.31
    ⦑
    2.30
    個人的には
    2.17
    お土産
    2.16
    我还是
    2.08
    2
    2.05
     verbess
    2.03
    6
    2.02
    Activations Density 0.000%

    No Known Activations