© 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-16K
    7. 2548
    Prev
    Next
    INDEX
    Explanations

    class declarations

    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_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
    defined
    0.48
    with
    0.42
    の種類
    0.42
    where
    0.41
    #,
    0.40
    ()
    0.40
     από
    0.39
     ssid
    0.39
     olmadan
    0.38
    lname
    0.38
    POSITIVE LOGITS
     esimerkiksi
    0.44
     B
    0.42
     ப்
    0.42
     Helper
    0.41
     bijvoorbeeld
    0.41
    Hydro
    0.40
     Quận
    0.40
     Z
    0.40
     bruker
    0.39
    PhysRev
    0.39
    Activations Density 0.143%

    No Known Activations