© 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. 56351
    Prev
    Next
    INDEX
    Explanations

    and fuel efficiency

    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
     impoverished
    0.42
     जन्माष्टमी
    0.42
    allery
    0.41
    开头
    0.41
    的感觉
    0.41
    include
    0.41
    ána
    0.41
    \
    0.41
     irritable
    0.40
    verm
    0.40
    POSITIVE LOGITS
    สัญญา
    0.44
     gás
    0.43
     incênd
    0.43
     parsing
    0.43
     warping
    0.43
     dataframe
    0.42
     resampling
    0.42
    運輸
    0.41
     refueling
    0.41
     DREAM
    0.40
    Activations Density 0.009%

    No Known Activations