© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125620
    Prev
    Next
    INDEX
    Explanations

    online courses and research

    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
     Cristina
    0.45
     TextAlign
    0.43
    Х
    0.43
     "!
    0.42
    ગુ
    0.41
     Times
    0.40
     எதி
    0.40
    უნქ
    0.39
     гу
    0.39
    зидент
    0.39
    POSITIVE LOGITS
    en
    0.55
    comput
    0.55
    et
    0.54
    igated
    0.54
    u
    0.54
    value
    0.53
    in
    0.52
    né
    0.51
    izace
    0.50
     überprü
    0.50
    Activations Density 0.000%

    No Known Activations