© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 197636
    Prev
    Next
    INDEX
    Explanations

    personal dataThis neuron detects/predicts personal data

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

    preferences and cults

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    0.45
    0.45
    `
    0.44
    </h2>
    0.42
     costs
    0.41
    judicial
    0.41
    charge
    0.40
    costs
    0.40
    Õ
    0.40
    Rem
    0.39
    POSITIVE LOGITS
    ໃຈ
    0.45
     saad
    0.44
     අපි
    0.44
    UNK
    0.44
     ಸುಬ್ಬ
    0.44
    鯢
    0.44
    unk
    0.43
     نبود
    0.43
    oyed
    0.43
     আসেনি
    0.43
    Activations Density 0.000%

    No Known Activations