© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53346
    Prev
    Next
    INDEX
    Explanations

    explaining robot instructions or technical concepts

    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
    िस्थित
    0.48
     simplistic
    0.45
    ו
    0.45
    ี
    0.45
     conservation
    0.44
     erkennen
    0.43
    environmental
    0.43
    皞
    0.43
    es
    0.42
    出来
    0.42
    POSITIVE LOGITS
     khoản
    0.46
     abusing
    0.46
     Hollywood
    0.45
     امور
    0.43
     internacionais
    0.42
     Parisian
    0.41
     Intense
    0.41
     internationaux
    0.41
     Angelina
    0.40
     दुरुपयोग
    0.40
    Activations Density 0.027%

    No Known Activations