© 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. 185925
    Prev
    Next
    INDEX
    Explanations

    IP Address collection

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

    consent and its lack

    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
    𝘫
    0.52
    太平
    0.51
    赵
    0.50
    Wir
    0.49
    przy
    0.49
    យើង
    0.48
    حمد
    0.48
    kimi
    0.47
    她的
    0.47
     Ком
    0.46
    POSITIVE LOGITS
     antimicrobial
    0.51
     divest
    0.51
     hippie
    0.50
     diva
    0.49
     extravagant
    0.49
    |,
    0.48
     dermatologist
    0.48
     ville
    0.47
     asthma
    0.47
     sphere
    0.46
    Activations Density 0.002%

    No Known Activations