© 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. 28734
    Prev
    Next
    INDEX
    Explanations

    drugs production fuels harm

    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
     geometric
    0.41
     geometri
    0.41
    ো
    0.39
     coeficiente
    0.38
     kosher
    0.38
     dedicar
    0.38
     nơi
    0.37
    spolit
    0.37
    shal
    0.37
     network
    0.37
    POSITIVE LOGITS
     بغیر
    0.46
     కూడా
    0.45
    ޑ
    0.44
     Reck
    0.44
    тические
    0.43
     грудня
    0.43
     Single
    0.43
     таксама
    0.43
    َّة
    0.43
     सिंगल
    0.42
    Activations Density 0.003%

    No Known Activations