© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11475
    Prev
    Next
    INDEX
    Explanations

    `](https`

    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_40_width_16k_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
     aman
    0.44
    ПО
    0.42
     безопасности
    0.41
    )&
    0.41
    inicio
    0.41
    房子
    0.40
     જન્મ
    0.40
    ους
    0.39
    captcha
    0.39
    ㄆ
    0.39
    POSITIVE LOGITS
     Cra
    0.43
     amounted
    0.41
     Improving
    0.41
     Analysts
    0.40
     Allowing
    0.40
     Consultez
    0.40
     Engineers
    0.39
     Correspond
    0.39
     Ashes
    0.39
     Remarkably
    0.38
    Activations Density 0.029%

    No Known Activations