© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33441
    Prev
    Next
    INDEX
    Explanations

    tokens following common words

    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_40_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
    ed
    0.44
    ful
    0.42
    Supply
    0.42
    Pers
    0.42
    Delivery
    0.40
    了
    0.39
    N
    0.39
     Supply
    0.38
    P
    0.38
    Ex
    0.38
    POSITIVE LOGITS
     bardziej
    0.41
     conceding
    0.41
     radiators
    0.41
    症状
    0.40
     plabic
    0.40
     interne
    0.39
     tyrann
    0.39
     ಎರ
    0.39
     vasculature
    0.39
     chaf
    0.39
    Activations Density 0.000%

    No Known Activations