© 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. 8555
    Prev
    Next
    INDEX
    Explanations

    Bank, agreements, but

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

    mental wellbeing

    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
    }>{
    0.24
    pipelines
    0.24
     ተመሳሳይ
    0.22
    >\
    0.22
    datatables
    0.22
     systematically
    0.22
    อด
    0.22
    projects
    0.22
    >
    0.22
    Projects
    0.21
    POSITIVE LOGITS
     essentials
    0.34
     hiszen
    0.29
    했지만
    0.28
     সুবিধ
    0.28
     lakini
    0.28
     but
    0.27
     però
    0.27
     Essentials
    0.27
     tentu
    0.27
     mutta
    0.27
    Activations Density 0.000%

    No Known Activations