© 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. 72447
    Prev
    Next
    INDEX
    Explanations

    not give

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

    learning, coding, hybrid, shops

    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
     armament
    0.45
     stretch
    0.40
     Cane
    0.40
     deadly
    0.38
     deset
    0.38
    \|$
    0.38
     arm
    0.38
     social
    0.38
     рад
    0.37
     minis
    0.37
    POSITIVE LOGITS
    栩
    0.54
    gsm
    0.51
    淙
    0.51
    gunakan
    0.48
    ąda
    0.48
    atação
    0.48
     increí
    0.47
    lıkla
    0.47
    祯
    0.46
    ঘ্রই
    0.46
    Activations Density 0.002%

    No Known Activations