© 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-262K
    7. 27012
    Prev
    Next
    INDEX
    Explanations

    on eye level

    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_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
    ５
    0.38
    融入
    0.37
    dives
    0.37
    >≤</
    0.35
    quele
    0.33
     كل
    0.33
     generalizations
    0.33
    riches
    0.32
    ٥
    0.32
     famili
    0.32
    POSITIVE LOGITS
     horseback
    0.53
    slaught
    0.53
     ON
    0.51
     On
    0.50
     behalf
    0.48
    liness
    0.44
     Oncol
    0.44
     निर्भर
    0.41
     وعلى
    0.40
    ;
    0.40
    Activations Density 0.013%

    No Known Activations