© 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. 51301
    Prev
    Next
    INDEX
    Explanations

    providing life's essentials

    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
     concerts
    0.47
    墩
    0.44
     mengalami
    0.44
     snail
    0.44
     smut
    0.43
     vandal
    0.40
    社會
    0.40
    }):
    0.39
    χή
    0.39
     birbir
    0.38
    POSITIVE LOGITS
     sustenance
    0.51
     제공
    0.47
     Versorgung
    0.46
     ресур
    0.44
    食物
    0.44
     nourishment
    0.44
     обеспечение
    0.43
    essential
    0.43
    食材
    0.43
     ஆதார
    0.43
    Activations Density 0.050%

    No Known Activations