© 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. 167975
    Prev
    Next
    INDEX
    Explanations

    referencing previous states

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

    Fibonacci and recursive sequences

    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
     potatoes
    0.39
     salmon
    0.39
    再
    0.38
    ειας
    0.38
     futurs
    0.38
     wastage
    0.38
     hyaluronic
    0.37
    Salmon
    0.37
    無限
    0.37
     dumplings
    0.37
    POSITIVE LOGITS
     botón
    0.43
    ​​
    0.42
    ografía
    0.41
     تول
    0.41
     GeoNames
    0.40
     kantor
    0.39
    ​
    0.39
     Fleet
    0.38
     Бі
    0.38
     পিতাম
    0.38
    Activations Density 0.000%

    No Known Activations