© 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. 72044
    Prev
    Next
    INDEX
    Explanations

    purchase or quantity comparisons

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

    average, genre, and selection

    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
     civilisation
    0.45
    ັ
    0.44
    world
    0.40
    wyr
    0.40
     দুনি
    0.40
    uj
    0.39
    ("$
    0.39
    留
    0.39
    Baba
    0.38
    adays
    0.38
    POSITIVE LOGITS
     ЗА
    0.48
     agree
    0.44
     outright
    0.43
     不是
    0.42
    㖷
    0.42
     engra
    0.41
     Montes
    0.41
     offens
    0.41
     مشکل
    0.41
     miglior
    0.41
    Activations Density 0.000%

    No Known Activations