© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5654
    Prev
    Next
    INDEX
    Explanations

    sand

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

    sand, sandbox, sandwich

    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_53_width_65k_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
    Ƒ
    0.43
    ությ
    0.41
    顓
    0.39
    🥦
    0.38
     चै
    0.38
    tcpHeader
    0.37
     Pfaff
    0.37
     Proton
    0.36
    浣
    0.36
    颛
    0.36
    POSITIVE LOGITS
     sand
    4.66
    Sand
    4.44
     Sand
    4.34
     SAND
    4.34
    SAND
    4.13
    sand
    4.03
     sands
    3.92
    砂
    3.83
    沙
    3.70
    サンド
    3.69
    Activations Density 0.196%

    No Known Activations