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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3985
    Prev
    Next
    INDEX
    Explanations

    actions or outcomes

    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
     essayé
    0.47
     `=`,
    0.44
     Questa
    0.41
     geprü
    0.41
     utc
    0.41
     από
    0.39
     multiprocessing
    0.39
     alemán
    0.38
    ﭔ
    0.38
     keras
    0.38
    POSITIVE LOGITS
     mitigate
    0.67
     prevent
    0.61
     enhance
    0.60
     facilitate
    0.60
     promotes
    0.60
     prevents
    0.59
     предотвра
    0.59
     meningkatkan
    0.57
     reduces
    0.56
     reduce
    0.56
    Activations Density 0.211%

    No Known Activations