© 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. 22825
    Prev
    Next
    INDEX
    Explanations

    astronomical discoveries

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

    celestial body identification and detection

    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
    entretien
    0.45
    ەك
    0.44
    czaj
    0.43
    Angleterre
    0.43
    伟大
    0.43
    🕴
    0.43
    Berat
    0.43
    specification
    0.42
    სახ
    0.42
    لمان
    0.42
    POSITIVE LOGITS
     detections
    0.50
     R
    0.50
     발견
    0.50
     C
    0.50
     T
    0.48
     detection
    0.48
     LD
    0.48
     discovery
    0.47
     cDNA
    0.47
     detected
    0.47
    Activations Density 0.008%

    No Known Activations