© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12974
    Prev
    Next
    INDEX
    Explanations

    syllables and common endings

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

    numbers, quantities, and totals

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    0.45
     triangulation
    0.42
     problems
    0.41
     ending
    0.41
     conditions
    0.40
     stub
    0.39
    ,
    0.39
     checks
    0.39
     results
    0.39
     purposes
    0.39
    POSITIVE LOGITS
     आरमारा
    0.55
    𝙣
    0.51
     বিজ্ঞানী
    0.47
    ണ്യ
    0.47
    नस
    0.46
    ‵
    0.45
    妠
    0.45
    நப
    0.45
     ආර
    0.45
    孅
    0.45
    Activations Density 0.000%

    No Known Activations