© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61863
    Prev
    Next
    INDEX
    Explanations

    locations and finances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icherweise
    0.54
    avacan
    0.48
     ideia
    0.48
    nett
    0.47
    笘
    0.47
    atmosphère
    0.46
     विषा
    0.46
    registrar
    0.46
     nostrum
    0.46
     γλώ
    0.46
    POSITIVE LOGITS
    ”
    0.47
     från
    0.45
     ಮೂಲಕ
    0.41
     carriages
    0.41
     من
    0.40
     barges
    0.40
     সহিংসতার
    0.40
     lov
    0.39
     projections
    0.38
     intrusions
    0.38
    Activations Density 0.018%

    No Known Activations