© 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. 172524
    Prev
    Next
    INDEX
    Explanations

    recognized by, cover up, apprehend one

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

    Egyptian Imagery, confidence score

    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
     Bulgaria
    0.43
     lockdown
    0.42
    できる
    0.40
    、
    0.40
     че
    0.39
     locked
    0.39
     goodbye
    0.38
     facilities
    0.38
    ені
    0.38
     leg
    0.38
    POSITIVE LOGITS
    פות
    0.57
    ותו
    0.55
     Algunos
    0.54
    ༢
    0.53
     برخی
    0.52
    റ്റ്
    0.52
     oWord
    0.50
     Ainsi
    0.50
    션
    0.50
    コイル
    0.50
    Activations Density 0.000%

    No Known Activations