© 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. 183631
    Prev
    Next
    INDEX
    Explanations

    online transactions or updates

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

    new hires or considerations

    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
    ཧ
    0.47
    راتكم
    0.46
     시작하겠습니다
    0.44
    指数
    0.43
    排行榜
    0.42
    行为
    0.41
    
    0.41
     pumpkin
    0.41
    UIManager
    0.41
    יר
    0.40
    POSITIVE LOGITS
    0.54
    ed
    0.50
    due
    0.47
     Vivek
    0.46
     due
    0.46
     finally
    0.46
     reaffirm
    0.46
     devido
    0.45
     reass
    0.44
    이다
    0.43
    Activations Density 0.001%

    No Known Activations