© 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-262K
    7. 127464
    Prev
    Next
    INDEX
    Explanations

    technical computing and data analysis

    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_262k_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
     naph
    0.48
     antimicrobial
    0.48
     sacrificing
    0.44
    炭
    0.44
     employment
    0.43
     antioxidant
    0.43
     canceling
    0.43
    항
    0.43
     ancestry
    0.42
     عد
    0.41
    POSITIVE LOGITS
     plików
    0.54
    8
    0.52
    File
    0.47
    şey
    0.46
     Trần
    0.46
    änge
    0.46
     świę
    0.45
     فائل
    0.42
    lee
    0.42
     ไฟล์
    0.41
    Activations Density 0.007%

    No Known Activations