© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54228
    Prev
    Next
    INDEX
    Explanations

    about:config

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     страте
    0.47
    debate
    0.44
     climates
    0.43
    integrate
    0.43
     казіно
    0.43
    зирован
    0.42
    늦
    0.41
     تحتاج
    0.41
     Свя
    0.41
     ಯಾವಾಗ
    0.40
    POSITIVE LOGITS
     kp
    0.45
    ností
    0.44
     km
    0.41
     ms
    0.41
     Hk
    0.41
    ଲେ
    0.41
     egen
    0.40
    ('/')
    0.40
     Putt
    0.40
    Dani
    0.39
    Activations Density 0.003%

    No Known Activations