© 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. 206136
    Prev
    Next
    INDEX
    Explanations

    regional National, about twice, space, my son

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

    Zapier, DataFrame, scene, Space

    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
     hoe
    0.46
    顔
    0.45
    βά
    0.45
    猴
    0.44
    髋
    0.42
     وہی
    0.41
    áo
    0.41
    群体
    0.40
    正月
    0.40
    徊
    0.40
    POSITIVE LOGITS
    edited
    0.53
    šit
    0.51
     yapmış
    0.48
     SMP
    0.47
    IsIn
    0.46
     በሚ
    0.46
     Juno
    0.46
    Inspect
    0.45
    contrar
    0.44
    ded
    0.44
    Activations Density 0.001%

    No Known Activations