© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142981
    Prev
    Next
    INDEX
    Explanations

    Beard Award

    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_262k_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
    radu
    0.46
     बढ़ाने
    0.44
     solemnly
    0.42
    usiasm
    0.42
    ,:
    0.41
     უნდა
    0.41
    rell
    0.41
    alog
    0.40
     सुझाव
    0.40
    Isra
    0.40
    POSITIVE LOGITS
    </h5>
    0.54
     dataset
    0.46
    </h2>
    0.45
     Dataset
    0.44
    路線
    0.44
     theatrical
    0.44
     judgmental
    0.43
     Route
    0.42
    </h3>
    0.42
     Region
    0.41
    Activations Density 0.010%

    No Known Activations