© 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. 124783
    Prev
    Next
    INDEX
    Explanations

    product types or names

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

    jokes, banker, doctor, year

    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
    l
    0.61
     from
    0.57
     that
    0.55
    m
    0.54
    n
    0.51
     colouring
    0.49
     mirror
    0.48
    al
    0.48
    م
    0.48
     lexicon
    0.47
    POSITIVE LOGITS
     ඔවුන්
    0.44
     ಅವರನ್ನು
    0.43
     \%(
    0.42
     συνέχεια
    0.42
     đội
    0.41
     ကျ
    0.40
     específicamente
    0.40
     بخش
    0.39
     kỷ
    0.39
     酸
    0.38
    Activations Density 0.000%

    No Known Activations