© 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. 204527
    Prev
    Next
    INDEX
    Explanations

    legal services, family matters

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

    AI, future, running processes

    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
     reduz
    0.47
    ة
    0.46
     diminu
    0.46
     jap
    0.45
     rezult
    0.45
     resulting
    0.45
     voce
    0.45
     instal
    0.45
    ((
    0.44
     över
    0.44
    POSITIVE LOGITS
    adiabatic
    0.49
    uyor
    0.48
     વખ
    0.47
    고
    0.47
    iacute
    0.46
    사가
    0.46
     प्राचीन
    0.45
    는데
    0.45
    اردوش
    0.45
    нди
    0.44
    Activations Density 0.000%

    No Known Activations