© 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. 196287
    Prev
    Next
    INDEX
    Explanations

    related to scheduling and terms

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

    roses are red, worms

    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
    o
    0.72
    ו
    0.57
     being
    0.51
    atin
    0.49
    u
    0.49
     litres
    0.49
     on
    0.49
     tape
    0.48
     currency
    0.47
    اران
    0.47
    POSITIVE LOGITS
     Entropy
    0.52
     Sasha
    0.50
     ไอ
    0.50
     Ét
    0.49
     Natasha
    0.48
    💹
    0.48
    шения
    0.47
     ราศี
    0.47
     живота
    0.47
     خوف
    0.47
    Activations Density 0.001%

    No Known Activations