© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63568
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    lists ending with 5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Beide
    0.42
     (**
    0.40
     analytics
    0.39
     दोनों
    0.38
    这两个
    0.38
     kedua
    0.37
     dialect
    0.37
     দুটো
    0.37
     contracts
    0.36
     BOTH
    0.36
    POSITIVE LOGITS
     всех
    0.44
    െല്ലാം
    0.42
     wszystkie
    0.42
    }+...
    0.41
    جميع
    0.39
    OLYBDENUM
    0.39
    冇
    0.38
     lahat
    0.38
    فو
    0.38
    \},
    0.37
    Activations Density 0.010%

    No Known Activations